The issues of seepage in calcareous sand foundations and backfillshave a potentially detrimental effect on the stability and safety of superstructures.Simplifying calcareous sand grains as spheres or ellipsoids in num...The issues of seepage in calcareous sand foundations and backfillshave a potentially detrimental effect on the stability and safety of superstructures.Simplifying calcareous sand grains as spheres or ellipsoids in numerical simulations may lead to significantinaccuracies.In this paper,we present a novel intelligence framework based on a deep convolutional generative adversarial network(DCGAN).A DCGAN model was trained using a training dataset comprising 11,625 real particles for the random generation of three-dimensional calcareous sand particles.Subsequently,3800 realistic calcareous sand particles with intra-particle voids were generated.Generative fidelityand validity of the DCGAN model were well verifiedby the consistency of the statistical values of nine morphological parameters of both the training dataset and the generated dataset.Digital calcareous sand columns were obtained through gravitational deposition simulation of the generated particles.Directional seepage simulations were conducted,and the vertical permeability values of the sand columns were found to be in accordance with the objective law.The results demonstrate the potential of the proposed framework for stochastic modeling and multi-scale simulation of the seepage behaviors in calcareous sand foundations and backfills.展开更多
While recent Gaussian-based SLAM methods achieve photorealistic reconstruction from RGB-D data, their computational performance remains a critical bottleneck. State-of-the-art techniques operate at less than 20 fps, s...While recent Gaussian-based SLAM methods achieve photorealistic reconstruction from RGB-D data, their computational performance remains a critical bottleneck. State-of-the-art techniques operate at less than 20 fps, significantly lagging behind geometry-based approaches like KinectFusion (hundreds of fps). This limitation stems from the heavy computational burden: modeling scenes requires numerous Gaussians and complex iterative optimization to fit RGB-D data;insufficient Gaussian counts or optimization iterations cause severe quality degradation. To address this, we propose a Gaussian-SDF hybrid representation, combining a colorized signed distance field (SDF) for smooth geometry and appearance with 3D Gaussians to capture underrepresented details. The SDF is efficiently constructed via RGB-D fusion (as in geometry-based methods), while Gaussians undergo iterative optimization. Our representation enables significant Gaussian reduction (50% fewer) by avoiding full-scene Gaussian modeling, and efficient Gaussian optimization (75% fewer iterations) through targeted appearance refinement. Building upon this representation, we develop GPS-SLAM (Gaussian-plus-SDF SLAM), a real-time 3D reconstruction system achieving over 150 fps on real-world Azure Kinect sequences, faster by an order-of-magnitude than state-of-the-art techniques while maintaining comparable reconstruction quality. The source code and data are available at https://gapszju.github.io/GPS-SLAM.展开更多
Three-dimensional(3D)scene reconstruction from the depth sensor is one of the fundamental research problems in many emerging applications such as robotic and virtual reality.However,due to the high computational compl...Three-dimensional(3D)scene reconstruction from the depth sensor is one of the fundamental research problems in many emerging applications such as robotic and virtual reality.However,due to the high computational complexity of 3D scene reconstruction processes,it is very difficult to achieve real-time implementation on low-power platforms.In this paper,we propose eTSDF,an energy-and memory-efficient hardware architecture for real-time truncated signed distance field(TSDF)-based 3D scene reconstruction system by accelerating the entire process stages on field-programmable gate array(FPGA)platform.To achieve memory-efficiency,we propose an adaptive TSDF integration solution,named eTSDF,which leverages the spatial locality of 3D volumetric representations and dynamically conducts integration process on sub-volumes,rather than on the entire volumes.In eTSDF,we design a set of dedicated,well optimized accelerators to achieve real-time implementations for the processes of adaptive sub-volume construction,coordinate transformation and TSDF integration.Evaluation results demonstrate that the eTSDF accelerator achieves up to 1.84×speedup and 101.23×energy efficiency improvement compared to the Intel i9-12900K CPU.展开更多
基金financially supported by the National Natural Science Foundation of China(Grant No.42077232)the National Natural Science Foundation for Excellent Young Scholars of China(Grant No.52222110)the Fundamental Research Funds for the Central Universities(Grant No.14380229).
文摘The issues of seepage in calcareous sand foundations and backfillshave a potentially detrimental effect on the stability and safety of superstructures.Simplifying calcareous sand grains as spheres or ellipsoids in numerical simulations may lead to significantinaccuracies.In this paper,we present a novel intelligence framework based on a deep convolutional generative adversarial network(DCGAN).A DCGAN model was trained using a training dataset comprising 11,625 real particles for the random generation of three-dimensional calcareous sand particles.Subsequently,3800 realistic calcareous sand particles with intra-particle voids were generated.Generative fidelityand validity of the DCGAN model were well verifiedby the consistency of the statistical values of nine morphological parameters of both the training dataset and the generated dataset.Digital calcareous sand columns were obtained through gravitational deposition simulation of the generated particles.Directional seepage simulations were conducted,and the vertical permeability values of the sand columns were found to be in accordance with the objective law.The results demonstrate the potential of the proposed framework for stochastic modeling and multi-scale simulation of the seepage behaviors in calcareous sand foundations and backfills.
基金supported by the National Natural Science Foundation of China(U23A20311,62421003).
文摘While recent Gaussian-based SLAM methods achieve photorealistic reconstruction from RGB-D data, their computational performance remains a critical bottleneck. State-of-the-art techniques operate at less than 20 fps, significantly lagging behind geometry-based approaches like KinectFusion (hundreds of fps). This limitation stems from the heavy computational burden: modeling scenes requires numerous Gaussians and complex iterative optimization to fit RGB-D data;insufficient Gaussian counts or optimization iterations cause severe quality degradation. To address this, we propose a Gaussian-SDF hybrid representation, combining a colorized signed distance field (SDF) for smooth geometry and appearance with 3D Gaussians to capture underrepresented details. The SDF is efficiently constructed via RGB-D fusion (as in geometry-based methods), while Gaussians undergo iterative optimization. Our representation enables significant Gaussian reduction (50% fewer) by avoiding full-scene Gaussian modeling, and efficient Gaussian optimization (75% fewer iterations) through targeted appearance refinement. Building upon this representation, we develop GPS-SLAM (Gaussian-plus-SDF SLAM), a real-time 3D reconstruction system achieving over 150 fps on real-world Azure Kinect sequences, faster by an order-of-magnitude than state-of-the-art techniques while maintaining comparable reconstruction quality. The source code and data are available at https://gapszju.github.io/GPS-SLAM.
文摘Three-dimensional(3D)scene reconstruction from the depth sensor is one of the fundamental research problems in many emerging applications such as robotic and virtual reality.However,due to the high computational complexity of 3D scene reconstruction processes,it is very difficult to achieve real-time implementation on low-power platforms.In this paper,we propose eTSDF,an energy-and memory-efficient hardware architecture for real-time truncated signed distance field(TSDF)-based 3D scene reconstruction system by accelerating the entire process stages on field-programmable gate array(FPGA)platform.To achieve memory-efficiency,we propose an adaptive TSDF integration solution,named eTSDF,which leverages the spatial locality of 3D volumetric representations and dynamically conducts integration process on sub-volumes,rather than on the entire volumes.In eTSDF,we design a set of dedicated,well optimized accelerators to achieve real-time implementations for the processes of adaptive sub-volume construction,coordinate transformation and TSDF integration.Evaluation results demonstrate that the eTSDF accelerator achieves up to 1.84×speedup and 101.23×energy efficiency improvement compared to the Intel i9-12900K CPU.
