Pub Date : 2022-10-12DOI: 10.48550/arXiv.2210.06240
Yu-An Liu, Chengjiang Long, Zhaoxuan Zhang, Bo Liu, Qiang Zhang, Baocai Yin, Xin Yang
3D scene graph generation (SGG) has been of high interest in computer vision. Although the accuracy of 3D SGG on coarse classification and single relation label has been gradually improved, the performance of existing works is still far from being perfect for fine-grained and multi-label situations. In this paper, we propose a framework fully exploring contextual information for the 3D SGG task, which attempts to satisfy the requirements of fine-grained entity class, multiple relation labels, and high accuracy simultaneously. Our proposed approach is composed of a Graph Feature Extraction module and a Graph Contextual Reasoning module, achieving appropriate information-redundancy feature extraction, structured organization, and hierarchical inferring. Our approach achieves superior or competitive performance over previous methods on the 3DSSG dataset, especially on the relationship prediction sub-task.
{"title":"Explore Contextual Information for 3D Scene Graph Generation","authors":"Yu-An Liu, Chengjiang Long, Zhaoxuan Zhang, Bo Liu, Qiang Zhang, Baocai Yin, Xin Yang","doi":"10.48550/arXiv.2210.06240","DOIUrl":"https://doi.org/10.48550/arXiv.2210.06240","url":null,"abstract":"3D scene graph generation (SGG) has been of high interest in computer vision. Although the accuracy of 3D SGG on coarse classification and single relation label has been gradually improved, the performance of existing works is still far from being perfect for fine-grained and multi-label situations. In this paper, we propose a framework fully exploring contextual information for the 3D SGG task, which attempts to satisfy the requirements of fine-grained entity class, multiple relation labels, and high accuracy simultaneously. Our proposed approach is composed of a Graph Feature Extraction module and a Graph Contextual Reasoning module, achieving appropriate information-redundancy feature extraction, structured organization, and hierarchical inferring. Our approach achieves superior or competitive performance over previous methods on the 3DSSG dataset, especially on the relationship prediction sub-task.","PeriodicalId":13376,"journal":{"name":"IEEE Transactions on Visualization and Computer Graphics","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2022-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44168847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the recent rise of Metaverse, online multiplayer VR applications are becoming increasingly prevalent worldwide. However, as multiple users are located in different physical environments, different reset frequencies and timings can lead to serious fairness issues for online collaborative/competitive VR applications. For the fairness of online VR apps/games, an ideal online RDW strategy must make the locomotion opportunities of different users equal, regardless of different physical environment layouts. The existing RDW methods lack the scheme to coordinate multiple users in different PEs, and thus have the issue of triggering too many resets for all the users under the locomotion fairness constraint. We propose a novel multi-user RDW method that is able to significantly reduce the overall reset number and give users a better immersive experience by providing a fair exploration. Our key idea is to first find out the "bottleneck" user that may cause all users to be reset and estimate the time to reset given the users' next targets, and then redirect all the users to favorable poses during that maximized bottleneck time to ensure the subsequent resets can be postponed as much as possible. More particularly, we develop methods to estimate the time of possibly encountering obstacles and the reachable area for a specific pose to enable the prediction of the next reset caused by any user. Our experiments and user study found that our method outperforms existing RDW methods in online VR applications.
{"title":"Multi-User Redirected Walking in Separate Physical Spaces for Online VR Scenarios","authors":"Sen-Zhe Xu, Jia-Hong Liu, Miao Wang, Fang-Lue Zhang, Songhai Zhang","doi":"10.48550/arXiv.2210.05356","DOIUrl":"https://doi.org/10.48550/arXiv.2210.05356","url":null,"abstract":"With the recent rise of Metaverse, online multiplayer VR applications are becoming increasingly prevalent worldwide. However, as multiple users are located in different physical environments, different reset frequencies and timings can lead to serious fairness issues for online collaborative/competitive VR applications. For the fairness of online VR apps/games, an ideal online RDW strategy must make the locomotion opportunities of different users equal, regardless of different physical environment layouts. The existing RDW methods lack the scheme to coordinate multiple users in different PEs, and thus have the issue of triggering too many resets for all the users under the locomotion fairness constraint. We propose a novel multi-user RDW method that is able to significantly reduce the overall reset number and give users a better immersive experience by providing a fair exploration. Our key idea is to first find out the \"bottleneck\" user that may cause all users to be reset and estimate the time to reset given the users' next targets, and then redirect all the users to favorable poses during that maximized bottleneck time to ensure the subsequent resets can be postponed as much as possible. More particularly, we develop methods to estimate the time of possibly encountering obstacles and the reachable area for a specific pose to enable the prediction of the next reset caused by any user. Our experiments and user study found that our method outperforms existing RDW methods in online VR applications.","PeriodicalId":13376,"journal":{"name":"IEEE Transactions on Visualization and Computer Graphics","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2022-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46927440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Traffic intersections are important scenes that can be seen almost everywhere in the traffic system. Currently, most simulation methods perform well at highways and urban traffic networks. In intersection scenarios, the challenge lies in the lack of clearly defined lanes, where agents with various motion plannings converge in the central area from different directions. Traditional model-based methods are difficult to drive agents to move realistically at intersections without enough predefined lanes, while data-driven methods often require a large amount of high-quality input data. Simultaneously, tedious parameter tuning is inevitable involved to obtain the desired simulation results. In this paper, we present a novel adaptive and planning-aware hybrid-driven method (TraInterSim) to simulate traffic intersection scenarios. Our hybrid-driven method combines an optimization-based data-driven scheme with a velocity continuity model. It guides the agent's movements using real-world data and can generate those behaviors not present in the input data. Our optimization method fully considers velocity continuity, desired speed, direction guidance, and planning-aware collision avoidance. Agents can perceive others' motion plannings and relative distances to avoid possible collisions. To preserve the individual flexibility of different agents, the parameters in our method are automatically adjusted during the simulation. TraInterSim can generate realistic behaviors of heterogeneous agents in different traffic intersection scenarios in interactive rates. Through extensive experiments as well as user studies, we validate the effectiveness and rationality of the proposed simulation method.
{"title":"TraInterSim: Adaptive and Planning-Aware Hybrid-Driven Traffic Intersection Simulation","authors":"Pei Lv, Xinming Pei, Xinyu Ren, Yuzhen Zhang, Chaochao Li, Mingliang Xu","doi":"10.48550/arXiv.2210.08118","DOIUrl":"https://doi.org/10.48550/arXiv.2210.08118","url":null,"abstract":"Traffic intersections are important scenes that can be seen almost everywhere in the traffic system. Currently, most simulation methods perform well at highways and urban traffic networks. In intersection scenarios, the challenge lies in the lack of clearly defined lanes, where agents with various motion plannings converge in the central area from different directions. Traditional model-based methods are difficult to drive agents to move realistically at intersections without enough predefined lanes, while data-driven methods often require a large amount of high-quality input data. Simultaneously, tedious parameter tuning is inevitable involved to obtain the desired simulation results. In this paper, we present a novel adaptive and planning-aware hybrid-driven method (TraInterSim) to simulate traffic intersection scenarios. Our hybrid-driven method combines an optimization-based data-driven scheme with a velocity continuity model. It guides the agent's movements using real-world data and can generate those behaviors not present in the input data. Our optimization method fully considers velocity continuity, desired speed, direction guidance, and planning-aware collision avoidance. Agents can perceive others' motion plannings and relative distances to avoid possible collisions. To preserve the individual flexibility of different agents, the parameters in our method are automatically adjusted during the simulation. TraInterSim can generate realistic behaviors of heterogeneous agents in different traffic intersection scenarios in interactive rates. Through extensive experiments as well as user studies, we validate the effectiveness and rationality of the proposed simulation method.","PeriodicalId":13376,"journal":{"name":"IEEE Transactions on Visualization and Computer Graphics","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2022-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47313608","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-27DOI: 10.1109/TVCG.2022.3209414
Huijie Guo, Meijun Liu, Bowen Yang, Ye Sun, Huamin Qu, Lei Shi
In the era of quantitative investment, factor-based investing models are widely adopted in the construction of stock portfolios. These models explain the performance of individual stocks by a set of financial factors, e.g., market beta and company size. In industry, open investment platforms allow the online building of factor-based models, yet set a high bar on the engineering expertise of end-users. State-of-the-art visualization systems integrate the whole factor investing pipeline, but do not directly address domain users' core requests on ranking factors and stocks for portfolio construction. The current model lacks explainability, which downgrades its credibility with stock investors. To fill the gap in modeling, ranking, and visualizing stock time series for factor investment, we designed and implemented a visual analytics system, namely RankFIRST. The system offers built-in support for an established factor collection and a cross-sectional regression model viable for human interpretation. A hierarchical slope graph design is introduced according to the desired characteristics of good factors for stock investment. A novel firework chart is also invented extending the well-known candlestick chart for stock time series. We evaluated the system on the full-scale Chinese stock market data in the recent 30 years. Case studies and controlled user evaluation demonstrate the superiority of our system on factor investing, in comparison to both passive investing on stock indices and existing stock market visual analytics tools.
{"title":"RankFIRST: Visual Analysis for Factor Investment By Ranking Stock Timeseries.","authors":"Huijie Guo, Meijun Liu, Bowen Yang, Ye Sun, Huamin Qu, Lei Shi","doi":"10.1109/TVCG.2022.3209414","DOIUrl":"10.1109/TVCG.2022.3209414","url":null,"abstract":"<p><p>In the era of quantitative investment, factor-based investing models are widely adopted in the construction of stock portfolios. These models explain the performance of individual stocks by a set of financial factors, e.g., market beta and company size. In industry, open investment platforms allow the online building of factor-based models, yet set a high bar on the engineering expertise of end-users. State-of-the-art visualization systems integrate the whole factor investing pipeline, but do not directly address domain users' core requests on ranking factors and stocks for portfolio construction. The current model lacks explainability, which downgrades its credibility with stock investors. To fill the gap in modeling, ranking, and visualizing stock time series for factor investment, we designed and implemented a visual analytics system, namely RankFIRST. The system offers built-in support for an established factor collection and a cross-sectional regression model viable for human interpretation. A hierarchical slope graph design is introduced according to the desired characteristics of good factors for stock investment. A novel firework chart is also invented extending the well-known candlestick chart for stock time series. We evaluated the system on the full-scale Chinese stock market data in the recent 30 years. Case studies and controlled user evaluation demonstrate the superiority of our system on factor investing, in comparison to both passive investing on stock indices and existing stock market visual analytics tools.</p>","PeriodicalId":13376,"journal":{"name":"IEEE Transactions on Visualization and Computer Graphics","volume":"PP ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2022-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9509274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-26DOI: 10.48550/arXiv.2209.12588
F. Ibarrola, Tomas Lawton, Kazjon Grace
Recent advances in text-conditioned generative models have provided us with neural networks capable of creating images of astonishing quality, be they realistic, abstract, or even creative. These models have in common that (more or less explicitly) they all aim to produce a high-quality one-off output given certain conditions, and in that they are not well suited for a creative collaboration framework. Drawing on theories from cognitive science that model how professional designers and artists think, we argue how this setting differs from the former and introduce CICADA: a Collaborative, Interactive Context-Aware Drawing Agent. CICADA uses a vector-based synthesis-by-optimisation method to take a partial sketch (such as might be provided by a user) and develop it towards a goal by adding and/or sensibly modifying traces. Given that this topic has been scarcely explored, we also introduce a way to evaluate desired characteristics of a model in this context by means of proposing a diversity measure. CICADA is shown to produce sketches of quality comparable to a human user's, enhanced diversity and most importantly to be able to cope with change by continuing the sketch minding the user's contributions in a flexible manner.
{"title":"A Collaborative, Interactive and Context-Aware Drawing Agent for Co-Creative Design","authors":"F. Ibarrola, Tomas Lawton, Kazjon Grace","doi":"10.48550/arXiv.2209.12588","DOIUrl":"https://doi.org/10.48550/arXiv.2209.12588","url":null,"abstract":"Recent advances in text-conditioned generative models have provided us with neural networks capable of creating images of astonishing quality, be they realistic, abstract, or even creative. These models have in common that (more or less explicitly) they all aim to produce a high-quality one-off output given certain conditions, and in that they are not well suited for a creative collaboration framework. Drawing on theories from cognitive science that model how professional designers and artists think, we argue how this setting differs from the former and introduce CICADA: a Collaborative, Interactive Context-Aware Drawing Agent. CICADA uses a vector-based synthesis-by-optimisation method to take a partial sketch (such as might be provided by a user) and develop it towards a goal by adding and/or sensibly modifying traces. Given that this topic has been scarcely explored, we also introduce a way to evaluate desired characteristics of a model in this context by means of proposing a diversity measure. CICADA is shown to produce sketches of quality comparable to a human user's, enhanced diversity and most importantly to be able to cope with change by continuing the sketch minding the user's contributions in a flexible manner.","PeriodicalId":13376,"journal":{"name":"IEEE Transactions on Visualization and Computer Graphics","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2022-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46267533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-19DOI: 10.48550/arXiv.2209.08884
Yushu Zhang, Jiahao Zhu, Mingfu Xue, Xinpeng Zhang, Xiaochun Cao
Current 3D mesh steganography algorithms relying on geometric modification are prone to detection by steganalyzers. In traditional steganography, adaptive steganography has proven to be an efficient means of enhancing steganography security. Taking inspiration from this, we propose a highly adaptive embedding algorithm, guided by the principle of minimizing a carefully crafted distortion through efficient steganography codes. Specifically, we tailor a payload-limited embedding optimization problem for 3D settings and devise a feature-preserving distortion (FPD) to measure the impact of message embedding. The distortion takes on an additive form and is defined as a weighted difference of the effective steganalytic subfeatures utilized by the current 3D steganalyzers. With practicality in mind, we refine the distortion to enhance robustness and computational efficiency. By minimizing the FPD, our algorithm can preserve mesh features to a considerable extent, including steganalytic and geometric features, while achieving a high embedding capacity. During the practical embedding phase, we employ the Q-layered syndrome trellis code (STC). However, calculating the bit modification probability (BMP) for each layer of the Q-layered STC, given the variation of Q, can be cumbersome. To address this issue, we design a universal and automatic approach for the BMP calculation. The experimental results demonstrate that our algorithm achieves state-of-the-art performance in countering 3D steganalysis.
{"title":"Adaptive 3D Mesh Steganography Based on Feature-Preserving Distortion","authors":"Yushu Zhang, Jiahao Zhu, Mingfu Xue, Xinpeng Zhang, Xiaochun Cao","doi":"10.48550/arXiv.2209.08884","DOIUrl":"https://doi.org/10.48550/arXiv.2209.08884","url":null,"abstract":"Current 3D mesh steganography algorithms relying on geometric modification are prone to detection by steganalyzers. In traditional steganography, adaptive steganography has proven to be an efficient means of enhancing steganography security. Taking inspiration from this, we propose a highly adaptive embedding algorithm, guided by the principle of minimizing a carefully crafted distortion through efficient steganography codes. Specifically, we tailor a payload-limited embedding optimization problem for 3D settings and devise a feature-preserving distortion (FPD) to measure the impact of message embedding. The distortion takes on an additive form and is defined as a weighted difference of the effective steganalytic subfeatures utilized by the current 3D steganalyzers. With practicality in mind, we refine the distortion to enhance robustness and computational efficiency. By minimizing the FPD, our algorithm can preserve mesh features to a considerable extent, including steganalytic and geometric features, while achieving a high embedding capacity. During the practical embedding phase, we employ the Q-layered syndrome trellis code (STC). However, calculating the bit modification probability (BMP) for each layer of the Q-layered STC, given the variation of Q, can be cumbersome. To address this issue, we design a universal and automatic approach for the BMP calculation. The experimental results demonstrate that our algorithm achieves state-of-the-art performance in countering 3D steganalysis.","PeriodicalId":13376,"journal":{"name":"IEEE Transactions on Visualization and Computer Graphics","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2022-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43256571","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Point cloud denoising is a fundamental and challenging problem in geometry processing. Existing methods typically involve direct denoising of noisy input or filtering raw normals followed by point position updates. Recognizing the crucial relationship between point cloud denoising and normal filtering, we re-examine this problem from a multitask perspective and propose an end-to-end network called PCDNF for joint normal filtering-based point cloud denoising. We introduce an auxiliary normal filtering task to enhance the network's ability to remove noise while preserving geometric features more accurately. Our network incorporates two novel modules. First, we design a shape-aware selector to improve noise removal performance by constructing latent tangent space representations for specific points, taking into account learned point and normal features as well as geometric priors. Second, we develop a feature refinement module to fuse point and normal features, capitalizing on the strengths of point features in describing geometric details and normal features in representing geometric structures, such as sharp edges and corners. This combination overcomes the limitations of each feature type and better recovers geometric information. Extensive evaluations, comparisons, and ablation studies demonstrate that the proposed method outperforms state-of-the-art approaches in both point cloud denoising and normal filtering.
{"title":"PCDNF: Revisiting Learning-based Point Cloud Denoising via Joint Normal Filtering","authors":"Zheng Liu, Sijing Zhan, Ya-Ou Zhao, Yuanyuan Liu, Renjie Chen, Ying He","doi":"10.48550/arXiv.2209.00798","DOIUrl":"https://doi.org/10.48550/arXiv.2209.00798","url":null,"abstract":"Point cloud denoising is a fundamental and challenging problem in geometry processing. Existing methods typically involve direct denoising of noisy input or filtering raw normals followed by point position updates. Recognizing the crucial relationship between point cloud denoising and normal filtering, we re-examine this problem from a multitask perspective and propose an end-to-end network called PCDNF for joint normal filtering-based point cloud denoising. We introduce an auxiliary normal filtering task to enhance the network's ability to remove noise while preserving geometric features more accurately. Our network incorporates two novel modules. First, we design a shape-aware selector to improve noise removal performance by constructing latent tangent space representations for specific points, taking into account learned point and normal features as well as geometric priors. Second, we develop a feature refinement module to fuse point and normal features, capitalizing on the strengths of point features in describing geometric details and normal features in representing geometric structures, such as sharp edges and corners. This combination overcomes the limitations of each feature type and better recovers geometric information. Extensive evaluations, comparisons, and ablation studies demonstrate that the proposed method outperforms state-of-the-art approaches in both point cloud denoising and normal filtering.","PeriodicalId":13376,"journal":{"name":"IEEE Transactions on Visualization and Computer Graphics","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2022-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43075765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-29DOI: 10.48550/arXiv.2208.13699
Zhiwei Tai, Leixian Shen, Enya Shen, Jianmin Wang
Node-link diagrams are widely used to visualize graphs. Most graph layout algorithms only use graph topology for aesthetic goals (e.g., minimize node occlusions and edge crossings) or use node attributes for exploration goals (e.g., preserve visible communities). Existing hybrid methods that bind the two perspectives still suffer from various generation restrictions (e.g., limited input types and required manual adjustments and prior knowledge of graphs) and the imbalance between aesthetic and exploration goals. In this paper, we propose a flexible embedding-based graph exploration pipeline to enjoy the best of both graph topology and node attributes. First, we leverage embedding algorithms for attributed graphs to encode the two perspectives into latent space. Then, we present an embedding-driven graph layout algorithm, GEGraph, which can achieve aesthetic layouts with better community preservation to support an easy interpretation of the graph structure. Next, graph explorations are extended based on the generated graph layout and insights extracted from the embedding vectors. Illustrated with examples, we build a layout-preserving aggregation method with Focus+Context interaction and a related nodes searching approach with multiple proximity strategies. Finally, we conduct quantitative and qualitative evaluations, a user study, and two case studies to validate our approach.
{"title":"Graph Exploration with Embedding-Guided Layouts","authors":"Zhiwei Tai, Leixian Shen, Enya Shen, Jianmin Wang","doi":"10.48550/arXiv.2208.13699","DOIUrl":"https://doi.org/10.48550/arXiv.2208.13699","url":null,"abstract":"Node-link diagrams are widely used to visualize graphs. Most graph layout algorithms only use graph topology for aesthetic goals (e.g., minimize node occlusions and edge crossings) or use node attributes for exploration goals (e.g., preserve visible communities). Existing hybrid methods that bind the two perspectives still suffer from various generation restrictions (e.g., limited input types and required manual adjustments and prior knowledge of graphs) and the imbalance between aesthetic and exploration goals. In this paper, we propose a flexible embedding-based graph exploration pipeline to enjoy the best of both graph topology and node attributes. First, we leverage embedding algorithms for attributed graphs to encode the two perspectives into latent space. Then, we present an embedding-driven graph layout algorithm, GEGraph, which can achieve aesthetic layouts with better community preservation to support an easy interpretation of the graph structure. Next, graph explorations are extended based on the generated graph layout and insights extracted from the embedding vectors. Illustrated with examples, we build a layout-preserving aggregation method with Focus+Context interaction and a related nodes searching approach with multiple proximity strategies. Finally, we conduct quantitative and qualitative evaluations, a user study, and two case studies to validate our approach.","PeriodicalId":13376,"journal":{"name":"IEEE Transactions on Visualization and Computer Graphics","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2022-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43234385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-25DOI: 10.48550/arXiv.2208.11905
Yiming Wang, Qingzhe Gao, Libin Liu, Lingjie Liu, C. Theobalt, B. Chen
We propose a new method for learning a generalized animatable neural human representation from a sparse set of multi-view imagery of multiple persons. The learned representation can be used to synthesize novel view images of an arbitrary person and further animate them with the user's pose control. While most existing methods can either generalize to new persons or synthesize animations with user control, none of them can achieve both at the same time. We attribute this accomplishment to the employment of a 3D proxy for a shared multi-person human model, and further the warping of the spaces of different poses to a shared canonical pose space, in which we learn a neural field and predict the person- and pose-dependent deformations, as well as appearance with the features extracted from input images. To cope with the complexity of the large variations in body shapes, poses, and clothing deformations, we design our neural human model with disentangled geometry and appearance. Furthermore, we utilize the image features both at the spatial point and on the surface points of the 3D proxy for predicting person- and pose-dependent properties. Experiments show that our method significantly outperforms the state-of-the-arts on both tasks.
{"title":"Neural Novel Actor: Learning a Generalized Animatable Neural Representation for Human Actors","authors":"Yiming Wang, Qingzhe Gao, Libin Liu, Lingjie Liu, C. Theobalt, B. Chen","doi":"10.48550/arXiv.2208.11905","DOIUrl":"https://doi.org/10.48550/arXiv.2208.11905","url":null,"abstract":"We propose a new method for learning a generalized animatable neural human representation from a sparse set of multi-view imagery of multiple persons. The learned representation can be used to synthesize novel view images of an arbitrary person and further animate them with the user's pose control. While most existing methods can either generalize to new persons or synthesize animations with user control, none of them can achieve both at the same time. We attribute this accomplishment to the employment of a 3D proxy for a shared multi-person human model, and further the warping of the spaces of different poses to a shared canonical pose space, in which we learn a neural field and predict the person- and pose-dependent deformations, as well as appearance with the features extracted from input images. To cope with the complexity of the large variations in body shapes, poses, and clothing deformations, we design our neural human model with disentangled geometry and appearance. Furthermore, we utilize the image features both at the spatial point and on the surface points of the 3D proxy for predicting person- and pose-dependent properties. Experiments show that our method significantly outperforms the state-of-the-arts on both tasks.","PeriodicalId":13376,"journal":{"name":"IEEE Transactions on Visualization and Computer Graphics","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48812024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-08-21DOI: 10.48550/arXiv.2208.10925
Hai Li, Xingrui Yang, Hongjia Zhai, Yuqian Liu, H. Bao, Guofeng Zhang
Virtual content creation and interaction play an important role in modern 3D applications. Recovering detailed 3D models from real scenes can significantly expand the scope of its applications and has been studied for decades in the computer vision and computer graphics community. In this work, we propose Vox-Surf, a voxel-based implicit surface representation. Our Vox-Surf divides the space into finite sparse voxels, where each voxel is a basic geometry unit that stores geometry and appearance information on its corner vertices. Due to the sparsity inherited from the voxel representation, Vox-Surf is suitable for almost any scene and can be easily trained end-to-end from multiple view images. We utilize a progressive training process to gradually cull out empty voxels and keep only valid voxels for further optimization, which greatly reduces the number of sample points and improves inference speed. Experiments show that our Vox-Surf representation can learn fine surface details and accurate colors with less memory and faster rendering than previous methods. The resulting fine voxels can also be considered as the bounding volumes for collision detection, which is useful in 3D interactions. We also show the potential application of Vox-Surf in scene editing and augmented reality. The source code is publicly available at https://github.com/zju3dv/Vox-Surf.
{"title":"Vox-Surf: Voxel-based Implicit Surface Representation","authors":"Hai Li, Xingrui Yang, Hongjia Zhai, Yuqian Liu, H. Bao, Guofeng Zhang","doi":"10.48550/arXiv.2208.10925","DOIUrl":"https://doi.org/10.48550/arXiv.2208.10925","url":null,"abstract":"Virtual content creation and interaction play an important role in modern 3D applications. Recovering detailed 3D models from real scenes can significantly expand the scope of its applications and has been studied for decades in the computer vision and computer graphics community. In this work, we propose Vox-Surf, a voxel-based implicit surface representation. Our Vox-Surf divides the space into finite sparse voxels, where each voxel is a basic geometry unit that stores geometry and appearance information on its corner vertices. Due to the sparsity inherited from the voxel representation, Vox-Surf is suitable for almost any scene and can be easily trained end-to-end from multiple view images. We utilize a progressive training process to gradually cull out empty voxels and keep only valid voxels for further optimization, which greatly reduces the number of sample points and improves inference speed. Experiments show that our Vox-Surf representation can learn fine surface details and accurate colors with less memory and faster rendering than previous methods. The resulting fine voxels can also be considered as the bounding volumes for collision detection, which is useful in 3D interactions. We also show the potential application of Vox-Surf in scene editing and augmented reality. The source code is publicly available at https://github.com/zju3dv/Vox-Surf.","PeriodicalId":13376,"journal":{"name":"IEEE Transactions on Visualization and Computer Graphics","volume":" ","pages":""},"PeriodicalIF":5.2,"publicationDate":"2022-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47088749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：