Yiming Wang, Qingzhe Gao, Libin Liu, Lingjie Liu, C. Theobalt, B. Chen
{"title":"神经新演员:学习人类演员的广义动画神经表示","authors":"Yiming Wang, Qingzhe Gao, Libin Liu, Lingjie Liu, C. Theobalt, B. Chen","doi":"10.48550/arXiv.2208.11905","DOIUrl":null,"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":4.7000,"publicationDate":"2022-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"9","resultStr":"{\"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\":null,\"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\":4.7000,\"publicationDate\":\"2022-08-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"9\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Visualization and Computer Graphics\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2208.11905\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, SOFTWARE ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Visualization and Computer Graphics","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.48550/arXiv.2208.11905","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, SOFTWARE ENGINEERING","Score":null,"Total":0}
Neural Novel Actor: Learning a Generalized Animatable Neural Representation for Human Actors
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.
期刊介绍:
TVCG is a scholarly, archival journal published monthly. Its Editorial Board strives to publish papers that present important research results and state-of-the-art seminal papers in computer graphics, visualization, and virtual reality. Specific topics include, but are not limited to: rendering technologies; geometric modeling and processing; shape analysis; graphics hardware; animation and simulation; perception, interaction and user interfaces; haptics; computational photography; high-dynamic range imaging and display; user studies and evaluation; biomedical visualization; volume visualization and graphics; visual analytics for machine learning; topology-based visualization; visual programming and software visualization; visualization in data science; virtual reality, augmented reality and mixed reality; advanced display technology, (e.g., 3D, immersive and multi-modal displays); applications of computer graphics and visualization.