In the decade of data explosion, a significant challenge is how to transform data into understandings and insights that are useful to people. Visualization, the use of computer-supported, interactive visual representa...In the decade of data explosion, a significant challenge is how to transform data into understandings and insights that are useful to people. Visualization, the use of computer-supported, interactive visual representations of data to amplify cognition, is an important approach to addressing this challenge. In particular, scientific visualization primarily represents physical or geometric data while information visualization mainly represents abstract data such as text documents, graphs, and multidimensional data. Visual analytics, springing out of the fields of information visualization and scientific visualization,展开更多
The use of pretrained backbones with finetuning has shown success for 2D vision and natural language processing tasks,with advantages over taskspecific networks.In this paper,we introduce a pretrained 3D backbone,call...The use of pretrained backbones with finetuning has shown success for 2D vision and natural language processing tasks,with advantages over taskspecific networks.In this paper,we introduce a pretrained 3D backbone,called Swin3D,for 3D indoor scene understanding.We designed a 3D Swin Transformer as our backbone network,which enables efficient selfattention on sparse voxels with linear memory complexity,making the backbone scalable to large models and datasets.We also introduce a generalized contextual relative positional embedding scheme to capture various irregularities of point signals for improved network performance.We pretrained a large Swin3D model on a synthetic Structured3D dataset,which is an order of magnitude larger than the ScanNet dataset.Our model pretrained on the synthetic dataset not only generalizes well to downstream segmentation and detection on real 3D point datasets but also outperforms state-of-the-art methods on downstream tasks with+2.3 mIoU and+2.2 mIoU on S3DIS Area5 and 6-fold semantic segmentation,respectively,+1.8 mIoU on ScanNet segmentation(val),+1.9 mAP@0.5 on ScanNet detection,and+8.1 mAP@0.5 on S3DIS detection.A series of extensive ablation studies further validated the scalability,generality,and superior performance enabled by our approach.展开更多
Visual analytics employs interactive visualizations to integrate users＇ knowledge and inference capability into numerical/algorithmic data analysis processes. It is an active research field that has applications in m...Visual analytics employs interactive visualizations to integrate users＇ knowledge and inference capability into numerical/algorithmic data analysis processes. It is an active research field that has applications in many sectors, such as security, finance, and business. The growing popularity of visual analytics in recent years creates the need for a broad survey that reviews and assesses the recent developments in the field. This report reviews and classifies recent work into a set of application categories including space and time, multivariate, text, graph and network, and other applications. More importantly, this report presents analytics space, inspired by design space, which relates each application category to the key steps in visual analytics, including visual mapping, model-based analysis, and user interactions. We explore and discuss the analytics space to acld the current understanding and better understand research trends in the field.展开更多
We present a simple yet effective method for constructing 3D self-supporting surfaces with planar quadrilateral(PQ)elements.Starting with a triangular discretization of a self-supporting surface,we firstcompute the pr...We present a simple yet effective method for constructing 3D self-supporting surfaces with planar quadrilateral(PQ)elements.Starting with a triangular discretization of a self-supporting surface,we firstcompute the principal curvatures and directions of each triangular face using a new discrete differential geometryapproach,yielding more accurate results than existing methods.Then,we smooth the principal direction field to reduce the number of singularities.Next,we partition all faces into two groups in terms of principalcurvature difference.For each face with small curvature difference,we compute a stretch matrix that turns the principal directions into a pair of conjugate directions.For the remaining triangular faces,we simply keep their smoothed principal directions.Finally,applying a mixed-integer programming solver to the mixed principal and conjugate direction field,we obtain a planar quadrilateral mesh.Experimental results show that our method is computationally efficient and can yield high-quality PQ meshes that well approximate the geometry of the input surfaces and maintain their self-supporting properties.展开更多
We present a sketch-based rotation editing mations. Given a set of keyframe orientations of a rigid system for enriching rotational motion in keyframe ani- object, the user first edits its angular velocity trajectory ...We present a sketch-based rotation editing mations. Given a set of keyframe orientations of a rigid system for enriching rotational motion in keyframe ani- object, the user first edits its angular velocity trajectory by sketching curves, and then the system computes the altered rotational motion by solving a variational curve fitting problem. The solved rotational motion not only satisfies the orientation constraints at the keyframes, but also fits well the user-specified angular velocity trajectory. Our system is simple and easy to use. We demonstrate its usefulness by adding interesting and realistic rotational details to several keyframe animations.展开更多
文摘In the decade of data explosion, a significant challenge is how to transform data into understandings and insights that are useful to people. Visualization, the use of computer-supported, interactive visual representations of data to amplify cognition, is an important approach to addressing this challenge. In particular, scientific visualization primarily represents physical or geometric data while information visualization mainly represents abstract data such as text documents, graphs, and multidimensional data. Visual analytics, springing out of the fields of information visualization and scientific visualization,
文摘The use of pretrained backbones with finetuning has shown success for 2D vision and natural language processing tasks,with advantages over taskspecific networks.In this paper,we introduce a pretrained 3D backbone,called Swin3D,for 3D indoor scene understanding.We designed a 3D Swin Transformer as our backbone network,which enables efficient selfattention on sparse voxels with linear memory complexity,making the backbone scalable to large models and datasets.We also introduce a generalized contextual relative positional embedding scheme to capture various irregularities of point signals for improved network performance.We pretrained a large Swin3D model on a synthetic Structured3D dataset,which is an order of magnitude larger than the ScanNet dataset.Our model pretrained on the synthetic dataset not only generalizes well to downstream segmentation and detection on real 3D point datasets but also outperforms state-of-the-art methods on downstream tasks with+2.3 mIoU and+2.2 mIoU on S3DIS Area5 and 6-fold semantic segmentation,respectively,+1.8 mIoU on ScanNet segmentation(val),+1.9 mAP@0.5 on ScanNet detection,and+8.1 mAP@0.5 on S3DIS detection.A series of extensive ablation studies further validated the scalability,generality,and superior performance enabled by our approach.
基金partly supported by the National Natural Science Foundation of China under Grant No. 61070114the Program for New Century Excellent Talents in University of China under Grant No. NCET-12-1087the Zhejiang Provincial Qianjiang Talents of China under Grant No. 2013R10054
文摘Visual analytics employs interactive visualizations to integrate users＇ knowledge and inference capability into numerical/algorithmic data analysis processes. It is an active research field that has applications in many sectors, such as security, finance, and business. The growing popularity of visual analytics in recent years creates the need for a broad survey that reviews and assesses the recent developments in the field. This report reviews and classifies recent work into a set of application categories including space and time, multivariate, text, graph and network, and other applications. More importantly, this report presents analytics space, inspired by design space, which relates each application category to the key steps in visual analytics, including visual mapping, model-based analysis, and user interactions. We explore and discuss the analytics space to acld the current understanding and better understand research trends in the field.
基金partially supported by National Natural Science Foundation of China(62172257,61802228)Singapore Ministry of Education(T2EP20220-0014)+1 种基金the RIE2020 Industry Alignment Fund-Industry Collaboration Projects(IAF-ICP)Funding Initiativecash and in-kind contribution from the industrial partner,Rolls-Royce.
文摘We present a simple yet effective method for constructing 3D self-supporting surfaces with planar quadrilateral(PQ)elements.Starting with a triangular discretization of a self-supporting surface,we firstcompute the principal curvatures and directions of each triangular face using a new discrete differential geometryapproach,yielding more accurate results than existing methods.Then,we smooth the principal direction field to reduce the number of singularities.Next,we partition all faces into two groups in terms of principalcurvature difference.For each face with small curvature difference,we compute a stretch matrix that turns the principal directions into a pair of conjugate directions.For the remaining triangular faces,we simply keep their smoothed principal directions.Finally,applying a mixed-integer programming solver to the mixed principal and conjugate direction field,we obtain a planar quadrilateral mesh.Experimental results show that our method is computationally efficient and can yield high-quality PQ meshes that well approximate the geometry of the input surfaces and maintain their self-supporting properties.
基金supported by the National Natural Science Foundation of China (No. 61003145)the Fundamental Research Fundsfor the Central Universities, China (No. 2009QNA5018)
文摘We present a sketch-based rotation editing mations. Given a set of keyframe orientations of a rigid system for enriching rotational motion in keyframe ani- object, the user first edits its angular velocity trajectory by sketching curves, and then the system computes the altered rotational motion by solving a variational curve fitting problem. The solved rotational motion not only satisfies the orientation constraints at the keyframes, but also fits well the user-specified angular velocity trajectory. Our system is simple and easy to use. We demonstrate its usefulness by adding interesting and realistic rotational details to several keyframe animations.
