Data augmentation plays an important role in boosting the performance of 3D models,while very few studies handle the 3D point cloud data with this technique.Global augmentation and cut-paste are commonly used augmenta...Data augmentation plays an important role in boosting the performance of 3D models,while very few studies handle the 3D point cloud data with this technique.Global augmentation and cut-paste are commonly used augmentation techniques for point clouds,where global augmentation is applied to the entire point cloud of the scene,and cut-paste samples objects from other frames into the current frame.Both types of data augmentation can improve performance,but the cut-paste technique cannot effectively deal with the occlusion relationship between the foreground object and the background scene and the rationality of object sampling,which may be counterproductive and may hurt the overall performance.In addition,LiDAR is susceptible to signal loss,external occlusion,extreme weather and other factors,which can easily cause object shape changes,while global augmentation and cut-paste cannot effectively enhance the robustness of the model.To this end,we propose Syn-Aug,a synchronous data augmentation framework for LiDAR-based 3D object detection.Specifically,we first propose a novel rendering-based object augmentation technique(Ren-Aug)to enrich training data while enhancing scene realism.Second,we propose a local augmentation technique(Local-Aug)to generate local noise by rotating and scaling objects in the scene while avoiding collisions,which can improve generalisation performance.Finally,we make full use of the structural information of 3D labels to make the model more robust by randomly changing the geometry of objects in the training frames.We verify the proposed framework with four different types of 3D object detectors.Experimental results show that our proposed Syn-Aug significantly improves the performance of various 3D object detectors in the KITTI and nuScenes datasets,proving the effectiveness and generality of Syn-Aug.On KITTI,four different types of baseline models using Syn-Aug improved mAP by 0.89%,1.35%,1.61%and 1.14%respectively.On nuScenes,four different types of baseline models using Syn-Aug improved mAP by 14.93%,10.42%,8.47%and 6.81%respectively.The code is available at https://github.com/liuhuaijjin/Syn-Aug.展开更多
Multi-modal 3D object detection has achieved remarkable progress,but it is often limited in practical industrial production because of its high cost and low efficiency.The multi-view camera-based method provides a fea...Multi-modal 3D object detection has achieved remarkable progress,but it is often limited in practical industrial production because of its high cost and low efficiency.The multi-view camera-based method provides a feasible solution due to its low cost.However,camera data lacks geometric depth,and only using camera data to obtain high accuracy is challenging.This paper proposes a multi-modal Bird-Eye-View(BEV)distillation framework(MMDistill)to make a trade-off between them.MMDistill is a carefully crafted two-stage distillation framework based on teacher and student models for learning cross-modal knowledge and generating multi-modal features.It can improve the performance of unimodal detectors without introducing additional costs during inference.Specifically,our method can effectively solve the cross-gap caused by the heterogeneity between data.Furthermore,we further propose a Light Detection and Ranging(LiDAR)-guided geometric compensation module,which can assist the student model in obtaining effective geometric features and reduce the gap between different modalities.Our proposed method generally requires fewer computational resources and faster inference speed than traditional multi-modal models.This advancement enables multi-modal technology to be applied more widely in practical scenarios.Through experiments,we validate the effectiveness and superiority of MMDistill on the nuScenes dataset,achieving an improvement of 4.1%mean Average Precision(mAP)and 4.6%NuScenes Detection Score(NDS)over the baseline detector.In addition,we also present detailed ablation studies to validate our method.展开更多
Monocular 3D object detection is challenging due to the lack of accurate depth information.Some methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input t...Monocular 3D object detection is challenging due to the lack of accurate depth information.Some methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input to augment the RGB images.Depth-based methods attempt to convert estimated depth maps to pseudo-LiDAR and then use LiDAR-based object detectors or focus on the perspective of image and depth fusion learning.However,they demonstrate limited performance and efficiency as a result of depth inaccuracy and complex fusion mode with convolutions.Different from these approaches,our proposed depth-guided vision transformer with a normalizing flows(NF-DVT)network uses normalizing flows to build priors in depth maps to achieve more accurate depth information.Then we develop a novel Swin-Transformer-based backbone with a fusion module to process RGB image patches and depth map patches with two separate branches and fuse them using cross-attention to exchange information with each other.Furthermore,with the help of pixel-wise relative depth values in depth maps,we develop new relative position embeddings in the cross-attention mechanism to capture more accurate sequence ordering of input tokens.Our method is the first Swin-Transformer-based backbone architecture for monocular 3D object detection.The experimental results on the KITTI and the challenging Waymo Open datasets show the effectiveness of our proposed method and superior performance over previous counterparts.展开更多
The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.I...The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.Inspired by the great progress of Transformer,we propose a novel general and robust voxel feature encoder for 3D object detection based on the traditional Transformer.We first investigate the permutation invariance of sequence data of the self-attention and apply it to point cloud processing.Then we construct a voxel feature layer based on the self-attention to adaptively learn local and robust context of a voxel according to the spatial relationship and context information exchanging between all points within the voxel.Lastly,we construct a general voxel feature learning framework with the voxel feature layer as the core for 3D object detection.The voxel feature with Transformer(VFT)can be plugged into any other voxel-based 3D object detection framework easily,and serves as the backbone for voxel feature extractor.Experiments results on the KITTI dataset demonstrate that our method achieves the state-of-the-art performance on 3D object detection.展开更多
In complex traffic environment scenarios,it is very important for autonomous vehicles to accurately perceive the dynamic information of other vehicles around the vehicle in advance.The accuracy of 3D object detection ...In complex traffic environment scenarios,it is very important for autonomous vehicles to accurately perceive the dynamic information of other vehicles around the vehicle in advance.The accuracy of 3D object detection will be affected by problems such as illumination changes,object occlusion,and object detection distance.To this purpose,we face these challenges by proposing a multimodal feature fusion network for 3D object detection(MFF-Net).In this research,this paper first uses the spatial transformation projection algorithm to map the image features into the feature space,so that the image features are in the same spatial dimension when fused with the point cloud features.Then,feature channel weighting is performed using an adaptive expression augmentation fusion network to enhance important network features,suppress useless features,and increase the directionality of the network to features.Finally,this paper increases the probability of false detection and missed detection in the non-maximum suppression algo-rithm by increasing the one-dimensional threshold.So far,this paper has constructed a complete 3D target detection network based on multimodal feature fusion.The experimental results show that the proposed achieves an average accuracy of 82.60%on the Karlsruhe Institute of Technology and Toyota Technological Institute(KITTI)dataset,outperforming previous state-of-the-art multimodal fusion networks.In Easy,Moderate,and hard evaluation indicators,the accuracy rate of this paper reaches 90.96%,81.46%,and 75.39%.This shows that the MFF-Net network has good performance in 3D object detection.展开更多
The high bandwidth and low latency of 6G network technology enable the successful application of monocular 3D object detection on vehicle platforms.Monocular 3D-object-detection-based Pseudo-LiDAR is a low-cost,lowpow...The high bandwidth and low latency of 6G network technology enable the successful application of monocular 3D object detection on vehicle platforms.Monocular 3D-object-detection-based Pseudo-LiDAR is a low-cost,lowpower solution compared to LiDAR solutions in the field of autonomous driving.However,this technique has some problems,i.e.,(1)the poor quality of generated Pseudo-LiDAR point clouds resulting from the nonlinear error distribution of monocular depth estimation and(2)the weak representation capability of point cloud features due to the neglected global geometric structure features of point clouds existing in LiDAR-based 3D detection networks.Therefore,we proposed a Pseudo-LiDAR confidence sampling strategy and a hierarchical geometric feature extraction module for monocular 3D object detection.We first designed a point cloud confidence sampling strategy based on a 3D Gaussian distribution to assign small confidence to the points with great error in depth estimation and filter them out according to the confidence.Then,we present a hierarchical geometric feature extraction module by aggregating the local neighborhood features and a dual transformer to capture the global geometric features in the point cloud.Finally,our detection framework is based on Point-Voxel-RCNN(PV-RCNN)with high-quality Pseudo-LiDAR and enriched geometric features as input.From the experimental results,our method achieves satisfactory results in monocular 3D object detection.展开更多
LIDAR point cloud-based 3D object detection aims to sense the surrounding environment by anchoring objects with the Bounding Box(BBox).However,under the three-dimensional space of autonomous driving scenes,the previou...LIDAR point cloud-based 3D object detection aims to sense the surrounding environment by anchoring objects with the Bounding Box(BBox).However,under the three-dimensional space of autonomous driving scenes,the previous object detection methods,due to the pre-processing of the original LIDAR point cloud into voxels or pillars,lose the coordinate information of the original point cloud,slow detection speed,and gain inaccurate bounding box positioning.To address the issues above,this study proposes a new two-stage network structure to extract point cloud features directly by PointNet++,which effectively preserves the original point cloud coordinate information.To improve the detection accuracy,a shell-based modeling method is proposed.It roughly determines which spherical shell the coordinates belong to.Then,the results are refined to ground truth,thereby narrowing the localization range and improving the detection accuracy.To improve the recall of 3D object detection with bounding boxes,this paper designs a self-attention module for 3D object detection with a skip connection structure.Some of these features are highlighted by weighting them on the feature dimensions.After training,it makes the feature weights that are favorable for object detection get larger.Thus,the extracted features are more adapted to the object detection task.Extensive comparison experiments and ablation experiments conducted on the KITTI dataset verify the effectiveness of our proposed method in improving recall and precision.展开更多
Point clouds and RGB images are both critical data for 3D object detection. While recent multi-modal methods combine them directly and show remarkable performances, they ignore the distinct forms of these two types of...Point clouds and RGB images are both critical data for 3D object detection. While recent multi-modal methods combine them directly and show remarkable performances, they ignore the distinct forms of these two types of data. For mitigating the influence of this intrinsic difference on performance, we propose a novel but effective fusion model named LI-Attention model, which takes both RGB features and point cloud features into consideration and assigns a weight to each RGB feature by attention mechanism.Furthermore, based on the LI-Attention model, we propose a 3D object detection method called image attention transformer network(IAT-Net) specialized for indoor RGB-D scene. Compared with previous work on multi-modal detection, IAT-Net fuses elaborate RGB features from 2D detection results with point cloud features in attention mechanism, meanwhile generates and refines 3D detection results with transformer model. Extensive experiments demonstrate that our approach outperforms stateof-the-art performance on two widely used benchmarks of indoor 3D object detection, SUN RGB-D and NYU Depth V2, while ablation studies have been provided to analyze the effect of each module. And the source code for the proposed IAT-Net is publicly available at https://github.com/wisper181/IAT-Net.展开更多
The inherent limitations of 2D object detection,such as inadequate spatial reasoning and susceptibility to environmental occlusions,pose significant risks to the safety and reliability of autonomous driving systems.To...The inherent limitations of 2D object detection,such as inadequate spatial reasoning and susceptibility to environmental occlusions,pose significant risks to the safety and reliability of autonomous driving systems.To address these challenges,this paper proposes an enhanced 3D object detection framework(FastSECOND)based on an optimized SECOND architecture,designed to achieve rapid and accurate perception in autonomous driving scenarios.Key innovations include:(1)Replacing the Rectified Linear Unit(ReLU)activation functions with the Gaussian Error Linear Unit(GELU)during voxel feature encoding and region proposal network stages,leveraging partial convolution to balance computational efficiency and detection accuracy;(2)Integrating a Swin-Transformer V2 module into the voxel backbone network to enhance feature extraction capabilities in sparse data;and(3)Introducing an optimized position regression loss combined with a geometry-aware Focal-EIoU loss function,which incorporates bounding box geometric correlations to accelerate network convergence.While this study currently focuses exclusively on the detection of the Car category,with experiments conducted on the Car class of the KITTI dataset,future work will extend to other categories such as Pedestrian and Cyclist to more comprehensively evaluate the generalization capability of the proposed framework.Extensive experimental results demonstrate that our framework achieves a more effective trade-off between detection accuracy and speed.Compared to the baseline SECOND model,it achieves a 21.9%relative improvement in 3D bounding box detection accuracy on the hard subset,while reducing inference time by 14 ms.These advancements underscore the framework’s potential for enabling real-time,high-precision perception in autonomous driving applications.展开更多
As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advan...As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advancing the development of perception technology in autonomous driving.To further promote the development of fusion algorithms and improve detection performance,this paper discusses the advantages and recent advancements of multimodal fusion-based object detection algorithms.Starting fromsingle-modal sensor detection,the paper provides a detailed overview of typical sensors used in autonomous driving and introduces object detection methods based on images and point clouds.For image-based detection methods,they are categorized into monocular detection and binocular detection based on different input types.For point cloud-based detection methods,they are classified into projection-based,voxel-based,point cluster-based,pillar-based,and graph structure-based approaches based on the technical pathways for processing point cloud features.Additionally,multimodal fusion algorithms are divided into Camera-LiDAR fusion,Camera-Radar fusion,Camera-LiDAR-Radar fusion,and other sensor fusion methods based on the types of sensors involved.Furthermore,the paper identifies five key future research directions in this field,aiming to provide insights for researchers engaged in multimodal fusion-based object detection algorithms and to encourage broader attention to the research and application of multimodal fusion-based object detection.展开更多
Aiming at the limitations of the existing railway foreign object detection methods based on two-dimensional(2D)images,such as short detection distance,strong influence of environment and lack of distance information,w...Aiming at the limitations of the existing railway foreign object detection methods based on two-dimensional(2D)images,such as short detection distance,strong influence of environment and lack of distance information,we propose Rail-PillarNet,a three-dimensional(3D)LIDAR(Light Detection and Ranging)railway foreign object detection method based on the improvement of PointPillars.Firstly,the parallel attention pillar encoder(PAPE)is designed to fully extract the features of the pillars and alleviate the problem of local fine-grained information loss in PointPillars pillars encoder.Secondly,a fine backbone network is designed to improve the feature extraction capability of the network by combining the coding characteristics of LIDAR point cloud feature and residual structure.Finally,the initial weight parameters of the model were optimised by the transfer learning training method to further improve accuracy.The experimental results on the OSDaR23 dataset show that the average accuracy of Rail-PillarNet reaches 58.51%,which is higher than most mainstream models,and the number of parameters is 5.49 M.Compared with PointPillars,the accuracy of each target is improved by 10.94%,3.53%,16.96%and 19.90%,respectively,and the number of parameters only increases by 0.64M,which achieves a balance between the number of parameters and accuracy.展开更多
This project explores the integration of image and point cloud data for 3D object detection using the F-PointNet model,aiming to enhance accuracy and reliability in autonomous driving applications.F-PointNet leverages...This project explores the integration of image and point cloud data for 3D object detection using the F-PointNet model,aiming to enhance accuracy and reliability in autonomous driving applications.F-PointNet leverages multimodal data from RGB cameras and LiDAR to improve environmental perception and object localisation under varied operational conditions.Employing a rigorous methodology,the model incorporates preprocessing and network components such as frustum rotation and T-net adjustments to refine the detection process.Experiments were conducted on the KITTI dataset,which included applying both random and designated perturbations,and assessing their impact on the model’s performance.Results show that random perturbations generally outperform designated ones,especially in complex scenarios,by enhancing the model’s adaptability and capability for generalisation.This study highlights the critical role of methodological innovations and data perturbation strategies in advancing 3D object detection technologies,suggesting that further research is needed to optimise these approaches for broader applications.Furthermore,this research contributes to the development of autonomous systems,emphasising the importance of robust and accurate 3D object detection in enhancing the safety and reliability of autonomous vehicles.展开更多
In recent years,camera-and lidar-based 3D object detection has achieved great progress.However,the related researches mainly focus on normal illumination conditions;the performance of their 3D detection algorithms wil...In recent years,camera-and lidar-based 3D object detection has achieved great progress.However,the related researches mainly focus on normal illumination conditions;the performance of their 3D detection algorithms will decrease under low lighting scenarios such as in the night.This work attempts to improve the fusion strategies on 3D vehicle detection accuracy in multiple lighting conditions.First,distance and uncertainty information is incorporated to guide the“painting”of semantic information onto point cloud during the data preprocessing.Moreover,a multitask framework is designed,which incorpo-rates uncertainty learning to improve detection accuracy under low-illumination scenarios.In the validation on KITTI and Dark-KITTI benchmark,the proposed method increases the vehicle detection accuracy on the KITTI benchmark by 1.35%and the generality of the model is validated on the proposed Dark-KITTI dataset,with a gain of 0.64%for vehicle detection.展开更多
3D object detection is a critical technology in many applications,and among the various detection methods,pointcloud-based methods have been the most popular research topic in recent years.Since Graph Neural Network(G...3D object detection is a critical technology in many applications,and among the various detection methods,pointcloud-based methods have been the most popular research topic in recent years.Since Graph Neural Network(GNN)is considered to be effective in dealing with pointclouds,in this work,we combined it with the attention mechanism and proposed a 3D object detection method named PointGAT.Our proposed PointGAT outperforms previous approaches on the KITTI test dataset.Experiments in real campus scenarios also demonstrate the potential of our method for further applications.展开更多
Lightweight modules play a key role in 3D object detection tasks for autonomous driving,which are necessary for the application of 3D object detectors.At present,research still focuses on constructing complex models a...Lightweight modules play a key role in 3D object detection tasks for autonomous driving,which are necessary for the application of 3D object detectors.At present,research still focuses on constructing complex models and calculations to improve the detection precision at the expense of the running rate.However,building a lightweight model to learn the global features from point cloud data for 3D object detection is a significant problem.In this paper,we focus on combining convolutional neural networks with selfattention-based vision transformers to realize lightweight and high-speed computing for 3D object detection.We propose lightweight detection 3D(LWD-3D),which is a point cloud conversion and lightweight vision transformer for autonomous driving.LWD-3D utilizes a one-shot regression framework in 2D space and generates a 3D object bounding box from point cloud data,which provides a new feature representation method based on a vision transformer for 3D detection applications.The results of experiment on the KITTI 3D dataset show that LWD-3D achieves real-time detection(time per image<20 ms).LWD-3D obtains a mean average precision(mAP)75%higher than that of another 3D real-time detector with half the number of parameters.Our research extends the application of visual transformers to 3D object detection tasks.展开更多
Relation contexts have been proved to be useful for many challenging vision tasks.In the field of3D object detection,previous methods have been taking the advantage of context encoding,graph embedding,or explicit rela...Relation contexts have been proved to be useful for many challenging vision tasks.In the field of3D object detection,previous methods have been taking the advantage of context encoding,graph embedding,or explicit relation reasoning to extract relation contexts.However,there exist inevitably redundant relation contexts due to noisy or low-quality proposals.In fact,invalid relation contexts usually indicate underlying scene misunderstanding and ambiguity,which may,on the contrary,reduce the performance in complex scenes.Inspired by recent attention mechanism like Transformer,we propose a novel 3D attention-based relation module(ARM3D).It encompasses objectaware relation reasoning to extract pair-wise relation contexts among qualified proposals and an attention module to distribute attention weights towards different relation contexts.In this way,ARM3D can take full advantage of the useful relation contexts and filter those less relevant or even confusing contexts,which mitigates the ambiguity in detection.We have evaluated the effectiveness of ARM3D by plugging it into several state-of-the-art 3D object detectors and showing more accurate and robust detection results.Extensive experiments show the capability and generalization of ARM3D on 3D object detection.Our source code is available at https://github.com/lanlan96/ARM3D.展开更多
The perception of Bird's Eye View(BEV)has become a widely adopted approach in 3D object detection due to its spatial and dimensional consistency.However,the increasing complexity of neural network architectures ha...The perception of Bird's Eye View(BEV)has become a widely adopted approach in 3D object detection due to its spatial and dimensional consistency.However,the increasing complexity of neural network architectures has resulted in higher training memory,thereby limiting the scalability of model training.To address these challenges,we propose a novel model,RevFB-BEV,which is based on the Reversible Swin Transformer(RevSwin)with Forward-Backward View Transformation(FBVT)and LiDAR Guided Back Projection(LGBP).This approach includes the RevSwin backbone network,which employs a reversible architecture to minimise training memory by recomputing intermediate parameters.Moreover,we introduce the FBVT module that refines BEV features extracted from forward projection,yielding denser and more precise camera BEV representations.The LGBP module further utilises LiDAR BEV guidance for back projection to achieve more accurate camera BEV features.Extensive experiments on the nuScenes dataset demonstrate notable performance improvements,with our model achieving over a 4 x reduction in training memory and a more than 12x decrease in single-backbone training memory.These efficiency gains become even more pronounced with deeper network architectures.Additionally,RevFB-BEV achieves 68.1 mAP(mean Average Precision)on the validation set and 68.9 mAP on the test set,which is nearly on par with the baseline BEVFusion,underscoring its effectiveness in resource-constrained scenarios.展开更多
In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is pro...In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is proposed,which makes use of multi-neighborhood information of voxel and image information.Firstly,design an improved ResNet that maintains the structure information of far and hard objects in low-resolution feature maps,which is more suitable for detection task.Meanwhile,semantema of each image feature map is enhanced by semantic information from all subsequent feature maps.Secondly,extract multi-neighborhood context information with different receptive field sizes to make up for the defect of sparseness of point cloud which improves the ability of voxel features to represent the spatial structure and semantic information of objects.Finally,propose a multi-modal feature adaptive fusion strategy which uses learnable weights to express the contribution of different modal features to the detection task,and voxel attention further enhances the fused feature expression of effective target objects.The experimental results on the KITTI benchmark show that this method outperforms VoxelNet with remarkable margins,i.e.increasing the AP by 8.78%and 5.49%on medium and hard difficulty levels.Meanwhile,our method achieves greater detection performance compared with many mainstream multi-modal methods,i.e.outperforming the AP by 1%compared with that of MVX-Net on medium and hard difficulty levels.展开更多
Light detection and ranging(LiDAR)sensors play a vital role in acquiring 3D point cloud data and extracting valuable information about objects for tasks such as autonomous driving,robotics,and virtual reality(VR).Howe...Light detection and ranging(LiDAR)sensors play a vital role in acquiring 3D point cloud data and extracting valuable information about objects for tasks such as autonomous driving,robotics,and virtual reality(VR).However,the sparse and disordered nature of the 3D point cloud poses significant challenges to feature extraction.Overcoming limitations is critical for 3D point cloud processing.3D point cloud object detection is a very challenging and crucial task,in which point cloud processing and feature extraction methods play a crucial role and have a significant impact on subsequent object detection performance.In this overview of outstanding work in object detection from the 3D point cloud,we specifically focus on summarizing methods employed in 3D point cloud processing.We introduce the way point clouds are processed in classical 3D object detection algorithms,and their improvements to solve the problems existing in point cloud processing.Different voxelization methods and point cloud sampling strategies will influence the extracted features,thereby impacting the final detection performance.展开更多
The task of detecting three-dimensional objects using only RGB images presents a considerable challenge within the domain of computer vision.The core issue lies in accurately performing epipolar geometry matching betw...The task of detecting three-dimensional objects using only RGB images presents a considerable challenge within the domain of computer vision.The core issue lies in accurately performing epipolar geometry matching between multiple views to obtain latent geometric priors.Existing methods establish correspondences along epipolar line features in voxel space through various layers of convolution.However,this step often occurs in the later stages of the network,which limits overall performance.To address this challenge,we introduce a novel framework,ImVoxelENet,that integrates a geometric epipolar constraint.We start from the back-projection of pixel-wise features and design an attention mechanism that captures the relationship between forward and backward features along the ray for multiple views.This approach enables the early establishment of geometric correspondences and structural connections between epipolar lines.Using ScanNetV2 as a benchmark,extensive comparative and ablation experiments demonstrate that our proposed network achieves a 1.1%improvement in mAP,highlighting its effectiveness in enhancing 3D object detection performance.Our code is available at https://github.com/xug-coder/ImVoxelENet.展开更多
基金supported by National Natural Science Foundation of China(61673186 and 61871196)Beijing Normal University Education Reform Project(jx2024040)Guangdong Undergraduate Universities Teaching Quality and Reform Project(jx2024309).
文摘Data augmentation plays an important role in boosting the performance of 3D models,while very few studies handle the 3D point cloud data with this technique.Global augmentation and cut-paste are commonly used augmentation techniques for point clouds,where global augmentation is applied to the entire point cloud of the scene,and cut-paste samples objects from other frames into the current frame.Both types of data augmentation can improve performance,but the cut-paste technique cannot effectively deal with the occlusion relationship between the foreground object and the background scene and the rationality of object sampling,which may be counterproductive and may hurt the overall performance.In addition,LiDAR is susceptible to signal loss,external occlusion,extreme weather and other factors,which can easily cause object shape changes,while global augmentation and cut-paste cannot effectively enhance the robustness of the model.To this end,we propose Syn-Aug,a synchronous data augmentation framework for LiDAR-based 3D object detection.Specifically,we first propose a novel rendering-based object augmentation technique(Ren-Aug)to enrich training data while enhancing scene realism.Second,we propose a local augmentation technique(Local-Aug)to generate local noise by rotating and scaling objects in the scene while avoiding collisions,which can improve generalisation performance.Finally,we make full use of the structural information of 3D labels to make the model more robust by randomly changing the geometry of objects in the training frames.We verify the proposed framework with four different types of 3D object detectors.Experimental results show that our proposed Syn-Aug significantly improves the performance of various 3D object detectors in the KITTI and nuScenes datasets,proving the effectiveness and generality of Syn-Aug.On KITTI,four different types of baseline models using Syn-Aug improved mAP by 0.89%,1.35%,1.61%and 1.14%respectively.On nuScenes,four different types of baseline models using Syn-Aug improved mAP by 14.93%,10.42%,8.47%and 6.81%respectively.The code is available at https://github.com/liuhuaijjin/Syn-Aug.
基金supported by the National Natural Science Foundation of China(GrantNo.62302086)the Natural Science Foundation of Liaoning Province(Grant No.2023-MSBA-070)the Fundamental Research Funds for the Central Universities(Grant No.N2317005).
文摘Multi-modal 3D object detection has achieved remarkable progress,but it is often limited in practical industrial production because of its high cost and low efficiency.The multi-view camera-based method provides a feasible solution due to its low cost.However,camera data lacks geometric depth,and only using camera data to obtain high accuracy is challenging.This paper proposes a multi-modal Bird-Eye-View(BEV)distillation framework(MMDistill)to make a trade-off between them.MMDistill is a carefully crafted two-stage distillation framework based on teacher and student models for learning cross-modal knowledge and generating multi-modal features.It can improve the performance of unimodal detectors without introducing additional costs during inference.Specifically,our method can effectively solve the cross-gap caused by the heterogeneity between data.Furthermore,we further propose a Light Detection and Ranging(LiDAR)-guided geometric compensation module,which can assist the student model in obtaining effective geometric features and reduce the gap between different modalities.Our proposed method generally requires fewer computational resources and faster inference speed than traditional multi-modal models.This advancement enables multi-modal technology to be applied more widely in practical scenarios.Through experiments,we validate the effectiveness and superiority of MMDistill on the nuScenes dataset,achieving an improvement of 4.1%mean Average Precision(mAP)and 4.6%NuScenes Detection Score(NDS)over the baseline detector.In addition,we also present detailed ablation studies to validate our method.
基金supported in part by the Major Project for New Generation of AI (2018AAA0100400)the National Natural Science Foundation of China (61836014,U21B2042,62072457,62006231)the InnoHK Program。
文摘Monocular 3D object detection is challenging due to the lack of accurate depth information.Some methods estimate the pixel-wise depth maps from off-the-shelf depth estimators and then use them as an additional input to augment the RGB images.Depth-based methods attempt to convert estimated depth maps to pseudo-LiDAR and then use LiDAR-based object detectors or focus on the perspective of image and depth fusion learning.However,they demonstrate limited performance and efficiency as a result of depth inaccuracy and complex fusion mode with convolutions.Different from these approaches,our proposed depth-guided vision transformer with a normalizing flows(NF-DVT)network uses normalizing flows to build priors in depth maps to achieve more accurate depth information.Then we develop a novel Swin-Transformer-based backbone with a fusion module to process RGB image patches and depth map patches with two separate branches and fuse them using cross-attention to exchange information with each other.Furthermore,with the help of pixel-wise relative depth values in depth maps,we develop new relative position embeddings in the cross-attention mechanism to capture more accurate sequence ordering of input tokens.Our method is the first Swin-Transformer-based backbone architecture for monocular 3D object detection.The experimental results on the KITTI and the challenging Waymo Open datasets show the effectiveness of our proposed method and superior performance over previous counterparts.
基金National Natural Science Foundation of China(No.61806006)Innovation Program for Graduate of Jiangsu Province(No.KYLX160-781)University Superior Discipline Construction Project of Jiangsu Province。
文摘The self-attention networks and Transformer have dominated machine translation and natural language processing fields,and shown great potential in image vision tasks such as image classification and object detection.Inspired by the great progress of Transformer,we propose a novel general and robust voxel feature encoder for 3D object detection based on the traditional Transformer.We first investigate the permutation invariance of sequence data of the self-attention and apply it to point cloud processing.Then we construct a voxel feature layer based on the self-attention to adaptively learn local and robust context of a voxel according to the spatial relationship and context information exchanging between all points within the voxel.Lastly,we construct a general voxel feature learning framework with the voxel feature layer as the core for 3D object detection.The voxel feature with Transformer(VFT)can be plugged into any other voxel-based 3D object detection framework easily,and serves as the backbone for voxel feature extractor.Experiments results on the KITTI dataset demonstrate that our method achieves the state-of-the-art performance on 3D object detection.
基金The authors would like to thank the financial support of Natural Science Foundation of Anhui Province(No.2208085MF173)the key research and development projects of Anhui(202104a05020003)+2 种基金the anhui development and reform commission supports R&D and innovation project([2020]479)the national natural science foundation of China(51575001)Anhui university scientific research platform innovation team building project(2016-2018).
文摘In complex traffic environment scenarios,it is very important for autonomous vehicles to accurately perceive the dynamic information of other vehicles around the vehicle in advance.The accuracy of 3D object detection will be affected by problems such as illumination changes,object occlusion,and object detection distance.To this purpose,we face these challenges by proposing a multimodal feature fusion network for 3D object detection(MFF-Net).In this research,this paper first uses the spatial transformation projection algorithm to map the image features into the feature space,so that the image features are in the same spatial dimension when fused with the point cloud features.Then,feature channel weighting is performed using an adaptive expression augmentation fusion network to enhance important network features,suppress useless features,and increase the directionality of the network to features.Finally,this paper increases the probability of false detection and missed detection in the non-maximum suppression algo-rithm by increasing the one-dimensional threshold.So far,this paper has constructed a complete 3D target detection network based on multimodal feature fusion.The experimental results show that the proposed achieves an average accuracy of 82.60%on the Karlsruhe Institute of Technology and Toyota Technological Institute(KITTI)dataset,outperforming previous state-of-the-art multimodal fusion networks.In Easy,Moderate,and hard evaluation indicators,the accuracy rate of this paper reaches 90.96%,81.46%,and 75.39%.This shows that the MFF-Net network has good performance in 3D object detection.
基金supported by the National Key Research and Development Program of China(2020YFB1807500)the National Natural Science Foundation of China(62072360,62001357,62172438,61901367)+4 种基金the key research and development plan of Shaanxi province(2021ZDLGY02-09,2023-GHZD-44,2023-ZDLGY-54)the Natural Science Foundation of Guangdong Province of China(2022A1515010988)Key Project on Artificial Intelligence of Xi'an Science and Technology Plan(2022JH-RGZN-0003,2022JH-RGZN-0103,2022JH-CLCJ-0053)Xi'an Science and Technology Plan(20RGZN0005)the Proof-ofconcept fund from Hangzhou Research Institute of Xidian University(GNYZ2023QC0201).
文摘The high bandwidth and low latency of 6G network technology enable the successful application of monocular 3D object detection on vehicle platforms.Monocular 3D-object-detection-based Pseudo-LiDAR is a low-cost,lowpower solution compared to LiDAR solutions in the field of autonomous driving.However,this technique has some problems,i.e.,(1)the poor quality of generated Pseudo-LiDAR point clouds resulting from the nonlinear error distribution of monocular depth estimation and(2)the weak representation capability of point cloud features due to the neglected global geometric structure features of point clouds existing in LiDAR-based 3D detection networks.Therefore,we proposed a Pseudo-LiDAR confidence sampling strategy and a hierarchical geometric feature extraction module for monocular 3D object detection.We first designed a point cloud confidence sampling strategy based on a 3D Gaussian distribution to assign small confidence to the points with great error in depth estimation and filter them out according to the confidence.Then,we present a hierarchical geometric feature extraction module by aggregating the local neighborhood features and a dual transformer to capture the global geometric features in the point cloud.Finally,our detection framework is based on Point-Voxel-RCNN(PV-RCNN)with high-quality Pseudo-LiDAR and enriched geometric features as input.From the experimental results,our method achieves satisfactory results in monocular 3D object detection.
基金This work was supported,in part,by the National Nature Science Foundation of China under grant numbers 62272236in part,by the Natural Science Foundation of Jiangsu Province under grant numbers BK20201136,BK20191401in part,by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fund.
文摘LIDAR point cloud-based 3D object detection aims to sense the surrounding environment by anchoring objects with the Bounding Box(BBox).However,under the three-dimensional space of autonomous driving scenes,the previous object detection methods,due to the pre-processing of the original LIDAR point cloud into voxels or pillars,lose the coordinate information of the original point cloud,slow detection speed,and gain inaccurate bounding box positioning.To address the issues above,this study proposes a new two-stage network structure to extract point cloud features directly by PointNet++,which effectively preserves the original point cloud coordinate information.To improve the detection accuracy,a shell-based modeling method is proposed.It roughly determines which spherical shell the coordinates belong to.Then,the results are refined to ground truth,thereby narrowing the localization range and improving the detection accuracy.To improve the recall of 3D object detection with bounding boxes,this paper designs a self-attention module for 3D object detection with a skip connection structure.Some of these features are highlighted by weighting them on the feature dimensions.After training,it makes the feature weights that are favorable for object detection get larger.Thus,the extracted features are more adapted to the object detection task.Extensive comparison experiments and ablation experiments conducted on the KITTI dataset verify the effectiveness of our proposed method in improving recall and precision.
基金supported by the National Natural Science Foundation of China (Grant No. 61803004)Aeronautical Science Foundation of China (Grant No. 20161375002)。
文摘Point clouds and RGB images are both critical data for 3D object detection. While recent multi-modal methods combine them directly and show remarkable performances, they ignore the distinct forms of these two types of data. For mitigating the influence of this intrinsic difference on performance, we propose a novel but effective fusion model named LI-Attention model, which takes both RGB features and point cloud features into consideration and assigns a weight to each RGB feature by attention mechanism.Furthermore, based on the LI-Attention model, we propose a 3D object detection method called image attention transformer network(IAT-Net) specialized for indoor RGB-D scene. Compared with previous work on multi-modal detection, IAT-Net fuses elaborate RGB features from 2D detection results with point cloud features in attention mechanism, meanwhile generates and refines 3D detection results with transformer model. Extensive experiments demonstrate that our approach outperforms stateof-the-art performance on two widely used benchmarks of indoor 3D object detection, SUN RGB-D and NYU Depth V2, while ablation studies have been provided to analyze the effect of each module. And the source code for the proposed IAT-Net is publicly available at https://github.com/wisper181/IAT-Net.
基金funded by the National Key R&D Program of China(Grant No.2022YFB4703400)the China Three Gorges Corporation(Grant No.2324020012)+2 种基金the National Natural Science Foundation of China(Grant No.62476080)the Jiangsu Province Natural Science Foundation(Grant No.BK20231186)Key Laboratory about Maritime Intelligent Network Information Technology of the Ministry of Education(EKLMIC202405).
文摘The inherent limitations of 2D object detection,such as inadequate spatial reasoning and susceptibility to environmental occlusions,pose significant risks to the safety and reliability of autonomous driving systems.To address these challenges,this paper proposes an enhanced 3D object detection framework(FastSECOND)based on an optimized SECOND architecture,designed to achieve rapid and accurate perception in autonomous driving scenarios.Key innovations include:(1)Replacing the Rectified Linear Unit(ReLU)activation functions with the Gaussian Error Linear Unit(GELU)during voxel feature encoding and region proposal network stages,leveraging partial convolution to balance computational efficiency and detection accuracy;(2)Integrating a Swin-Transformer V2 module into the voxel backbone network to enhance feature extraction capabilities in sparse data;and(3)Introducing an optimized position regression loss combined with a geometry-aware Focal-EIoU loss function,which incorporates bounding box geometric correlations to accelerate network convergence.While this study currently focuses exclusively on the detection of the Car category,with experiments conducted on the Car class of the KITTI dataset,future work will extend to other categories such as Pedestrian and Cyclist to more comprehensively evaluate the generalization capability of the proposed framework.Extensive experimental results demonstrate that our framework achieves a more effective trade-off between detection accuracy and speed.Compared to the baseline SECOND model,it achieves a 21.9%relative improvement in 3D bounding box detection accuracy on the hard subset,while reducing inference time by 14 ms.These advancements underscore the framework’s potential for enabling real-time,high-precision perception in autonomous driving applications.
基金funded by the Yangtze River Delta Science and Technology Innovation Community Joint Research Project(2023CSJGG1600)the Natural Science Foundation of Anhui Province(2208085MF173)Wuhu“ChiZhu Light”Major Science and Technology Project(2023ZD01,2023ZD03).
文摘As the number and complexity of sensors in autonomous vehicles continue to rise,multimodal fusionbased object detection algorithms are increasingly being used to detect 3D environmental information,significantly advancing the development of perception technology in autonomous driving.To further promote the development of fusion algorithms and improve detection performance,this paper discusses the advantages and recent advancements of multimodal fusion-based object detection algorithms.Starting fromsingle-modal sensor detection,the paper provides a detailed overview of typical sensors used in autonomous driving and introduces object detection methods based on images and point clouds.For image-based detection methods,they are categorized into monocular detection and binocular detection based on different input types.For point cloud-based detection methods,they are classified into projection-based,voxel-based,point cluster-based,pillar-based,and graph structure-based approaches based on the technical pathways for processing point cloud features.Additionally,multimodal fusion algorithms are divided into Camera-LiDAR fusion,Camera-Radar fusion,Camera-LiDAR-Radar fusion,and other sensor fusion methods based on the types of sensors involved.Furthermore,the paper identifies five key future research directions in this field,aiming to provide insights for researchers engaged in multimodal fusion-based object detection algorithms and to encourage broader attention to the research and application of multimodal fusion-based object detection.
基金supported by a grant from the National Key Research and Development Project(2023YFB4302100)Key Research and Development Project of Jiangxi Province(No.20232ACE01011)Independent Deployment Project of Ganjiang Innovation Research Institute,Chinese Academy of Sciences(E255J001).
文摘Aiming at the limitations of the existing railway foreign object detection methods based on two-dimensional(2D)images,such as short detection distance,strong influence of environment and lack of distance information,we propose Rail-PillarNet,a three-dimensional(3D)LIDAR(Light Detection and Ranging)railway foreign object detection method based on the improvement of PointPillars.Firstly,the parallel attention pillar encoder(PAPE)is designed to fully extract the features of the pillars and alleviate the problem of local fine-grained information loss in PointPillars pillars encoder.Secondly,a fine backbone network is designed to improve the feature extraction capability of the network by combining the coding characteristics of LIDAR point cloud feature and residual structure.Finally,the initial weight parameters of the model were optimised by the transfer learning training method to further improve accuracy.The experimental results on the OSDaR23 dataset show that the average accuracy of Rail-PillarNet reaches 58.51%,which is higher than most mainstream models,and the number of parameters is 5.49 M.Compared with PointPillars,the accuracy of each target is improved by 10.94%,3.53%,16.96%and 19.90%,respectively,and the number of parameters only increases by 0.64M,which achieves a balance between the number of parameters and accuracy.
文摘This project explores the integration of image and point cloud data for 3D object detection using the F-PointNet model,aiming to enhance accuracy and reliability in autonomous driving applications.F-PointNet leverages multimodal data from RGB cameras and LiDAR to improve environmental perception and object localisation under varied operational conditions.Employing a rigorous methodology,the model incorporates preprocessing and network components such as frustum rotation and T-net adjustments to refine the detection process.Experiments were conducted on the KITTI dataset,which included applying both random and designated perturbations,and assessing their impact on the model’s performance.Results show that random perturbations generally outperform designated ones,especially in complex scenarios,by enhancing the model’s adaptability and capability for generalisation.This study highlights the critical role of methodological innovations and data perturbation strategies in advancing 3D object detection technologies,suggesting that further research is needed to optimise these approaches for broader applications.Furthermore,this research contributes to the development of autonomous systems,emphasising the importance of robust and accurate 3D object detection in enhancing the safety and reliability of autonomous vehicles.
基金supported by the National Natural Science Foundation of China(No.52002285)the Shanghai Pujiang Program(No.2020PJD075)the Natural Science Foundation of Shanghai(No.21ZR1467400).
文摘In recent years,camera-and lidar-based 3D object detection has achieved great progress.However,the related researches mainly focus on normal illumination conditions;the performance of their 3D detection algorithms will decrease under low lighting scenarios such as in the night.This work attempts to improve the fusion strategies on 3D vehicle detection accuracy in multiple lighting conditions.First,distance and uncertainty information is incorporated to guide the“painting”of semantic information onto point cloud during the data preprocessing.Moreover,a multitask framework is designed,which incorpo-rates uncertainty learning to improve detection accuracy under low-illumination scenarios.In the validation on KITTI and Dark-KITTI benchmark,the proposed method increases the vehicle detection accuracy on the KITTI benchmark by 1.35%and the generality of the model is validated on the proposed Dark-KITTI dataset,with a gain of 0.64%for vehicle detection.
基金This work was supported in part by the Gansu Provincial Science and Technology Major Special Innovation Consortium Project(No.21ZD3GA002).
文摘3D object detection is a critical technology in many applications,and among the various detection methods,pointcloud-based methods have been the most popular research topic in recent years.Since Graph Neural Network(GNN)is considered to be effective in dealing with pointclouds,in this work,we combined it with the attention mechanism and proposed a 3D object detection method named PointGAT.Our proposed PointGAT outperforms previous approaches on the KITTI test dataset.Experiments in real campus scenarios also demonstrate the potential of our method for further applications.
基金supported by the National Natural Science Foundation of China(No.62206237)Japan Science Promotion Society(Nos.22K12093 and 22K12094)Japan Science and Technology Agency(No.JPMJST2281).
文摘Lightweight modules play a key role in 3D object detection tasks for autonomous driving,which are necessary for the application of 3D object detectors.At present,research still focuses on constructing complex models and calculations to improve the detection precision at the expense of the running rate.However,building a lightweight model to learn the global features from point cloud data for 3D object detection is a significant problem.In this paper,we focus on combining convolutional neural networks with selfattention-based vision transformers to realize lightweight and high-speed computing for 3D object detection.We propose lightweight detection 3D(LWD-3D),which is a point cloud conversion and lightweight vision transformer for autonomous driving.LWD-3D utilizes a one-shot regression framework in 2D space and generates a 3D object bounding box from point cloud data,which provides a new feature representation method based on a vision transformer for 3D detection applications.The results of experiment on the KITTI 3D dataset show that LWD-3D achieves real-time detection(time per image<20 ms).LWD-3D obtains a mean average precision(mAP)75%higher than that of another 3D real-time detector with half the number of parameters.Our research extends the application of visual transformers to 3D object detection tasks.
基金National Nature Science Foundation of China(62132021,62102435,62002375,62002376)National Key R&D Program of China(2018AAA0102200)NUDT Research Grants(ZK19-30)。
文摘Relation contexts have been proved to be useful for many challenging vision tasks.In the field of3D object detection,previous methods have been taking the advantage of context encoding,graph embedding,or explicit relation reasoning to extract relation contexts.However,there exist inevitably redundant relation contexts due to noisy or low-quality proposals.In fact,invalid relation contexts usually indicate underlying scene misunderstanding and ambiguity,which may,on the contrary,reduce the performance in complex scenes.Inspired by recent attention mechanism like Transformer,we propose a novel 3D attention-based relation module(ARM3D).It encompasses objectaware relation reasoning to extract pair-wise relation contexts among qualified proposals and an attention module to distribute attention weights towards different relation contexts.In this way,ARM3D can take full advantage of the useful relation contexts and filter those less relevant or even confusing contexts,which mitigates the ambiguity in detection.We have evaluated the effectiveness of ARM3D by plugging it into several state-of-the-art 3D object detectors and showing more accurate and robust detection results.Extensive experiments show the capability and generalization of ARM3D on 3D object detection.Our source code is available at https://github.com/lanlan96/ARM3D.
基金supported by the Baima Lake Laboratory Joint Funds of the Zhejiang Provincial Natural Science Foundation of China under Grant LBMHD25F030001in part by NSFC No.62088101+1 种基金The authors certify that there are no competing financial interests or personal relationships influencing this work.Financial support originated exclusively from public research funds:(1)Baima Lake Laboratory Joint Funds(Zhejiang Provincial NSF,China)Grant LBMHD25F030001National Natural Science Foundation of China Grant 62088101 for the'Autonomous Intelligent Unmanned Systems'project.
文摘The perception of Bird's Eye View(BEV)has become a widely adopted approach in 3D object detection due to its spatial and dimensional consistency.However,the increasing complexity of neural network architectures has resulted in higher training memory,thereby limiting the scalability of model training.To address these challenges,we propose a novel model,RevFB-BEV,which is based on the Reversible Swin Transformer(RevSwin)with Forward-Backward View Transformation(FBVT)and LiDAR Guided Back Projection(LGBP).This approach includes the RevSwin backbone network,which employs a reversible architecture to minimise training memory by recomputing intermediate parameters.Moreover,we introduce the FBVT module that refines BEV features extracted from forward projection,yielding denser and more precise camera BEV representations.The LGBP module further utilises LiDAR BEV guidance for back projection to achieve more accurate camera BEV features.Extensive experiments on the nuScenes dataset demonstrate notable performance improvements,with our model achieving over a 4 x reduction in training memory and a more than 12x decrease in single-backbone training memory.These efficiency gains become even more pronounced with deeper network architectures.Additionally,RevFB-BEV achieves 68.1 mAP(mean Average Precision)on the validation set and 68.9 mAP on the test set,which is nearly on par with the baseline BEVFusion,underscoring its effectiveness in resource-constrained scenarios.
基金National Youth Natural Science Foundation of China(No.61806006)Innovation Program for Graduate of Jiangsu Province(No.KYLX160-781)Jiangsu University Superior Discipline Construction Project。
文摘In order to solve difficult detection of far and hard objects due to the sparseness and insufficient semantic information of LiDAR point cloud,a 3D object detection network with multi-modal data adaptive fusion is proposed,which makes use of multi-neighborhood information of voxel and image information.Firstly,design an improved ResNet that maintains the structure information of far and hard objects in low-resolution feature maps,which is more suitable for detection task.Meanwhile,semantema of each image feature map is enhanced by semantic information from all subsequent feature maps.Secondly,extract multi-neighborhood context information with different receptive field sizes to make up for the defect of sparseness of point cloud which improves the ability of voxel features to represent the spatial structure and semantic information of objects.Finally,propose a multi-modal feature adaptive fusion strategy which uses learnable weights to express the contribution of different modal features to the detection task,and voxel attention further enhances the fused feature expression of effective target objects.The experimental results on the KITTI benchmark show that this method outperforms VoxelNet with remarkable margins,i.e.increasing the AP by 8.78%and 5.49%on medium and hard difficulty levels.Meanwhile,our method achieves greater detection performance compared with many mainstream multi-modal methods,i.e.outperforming the AP by 1%compared with that of MVX-Net on medium and hard difficulty levels.
文摘Light detection and ranging(LiDAR)sensors play a vital role in acquiring 3D point cloud data and extracting valuable information about objects for tasks such as autonomous driving,robotics,and virtual reality(VR).However,the sparse and disordered nature of the 3D point cloud poses significant challenges to feature extraction.Overcoming limitations is critical for 3D point cloud processing.3D point cloud object detection is a very challenging and crucial task,in which point cloud processing and feature extraction methods play a crucial role and have a significant impact on subsequent object detection performance.In this overview of outstanding work in object detection from the 3D point cloud,we specifically focus on summarizing methods employed in 3D point cloud processing.We introduce the way point clouds are processed in classical 3D object detection algorithms,and their improvements to solve the problems existing in point cloud processing.Different voxelization methods and point cloud sampling strategies will influence the extracted features,thereby impacting the final detection performance.
文摘The task of detecting three-dimensional objects using only RGB images presents a considerable challenge within the domain of computer vision.The core issue lies in accurately performing epipolar geometry matching between multiple views to obtain latent geometric priors.Existing methods establish correspondences along epipolar line features in voxel space through various layers of convolution.However,this step often occurs in the later stages of the network,which limits overall performance.To address this challenge,we introduce a novel framework,ImVoxelENet,that integrates a geometric epipolar constraint.We start from the back-projection of pixel-wise features and design an attention mechanism that captures the relationship between forward and backward features along the ray for multiple views.This approach enables the early establishment of geometric correspondences and structural connections between epipolar lines.Using ScanNetV2 as a benchmark,extensive comparative and ablation experiments demonstrate that our proposed network achieves a 1.1%improvement in mAP,highlighting its effectiveness in enhancing 3D object detection performance.Our code is available at https://github.com/xug-coder/ImVoxelENet.
