About The Forum
Calendar 2017 Poster Sessions : A Point Set Generation Network for 3D Object Reconstruction from a Single Image
Abstract:
Generation of 3D data by deep neural network has been attracting increasing attention in the research community. The majority of extant works resort to regular representations such as volumetric grids or collection of images; however, these representations obscure the natural invariance of 3D shapes under geometric transformations, and also suffer from a number of other issues. In this paper we address the problem of 3D reconstruction from a single image, generating a straight-forward form of output – point cloud coordinates. Along with this problem arises a unique and interesting issue, that the groundtruth shape for an input image may be ambiguous. Driven by this unorthodox output form and the inherent ambiguity in groundtruth, we design architecture, loss function and learning paradigm that are novel and effective. Our final solution is a conditional shape sampler, capable of predicting multiple plausible 3D point clouds from an input image. In experiments not only can our system outperform state-ofthe-art methods on single image based 3d reconstruction benchmarks; but it also shows strong performance for 3d shape completion and promising ability in making multiple plausible predictions.
Bio:
Hao Su is currently a Ph.D. candidate in the Computer Science Department of Stanford University. He is a member of Stanford AI Lab and Geometric Computing Lab. Hao’s research interests are broad, spanning computer vision, computer graphics, machine learning, and robotics. He is particularly interested in deep learning for 3D data understanding and interconnecting 3D data with other modalities such as images and texts. Hao has published papers at CVPR, ICCV, NIPS, ICML, SIGGRAPH, SIGGRAPH Asia, VLDB, SIGSPATIAL, IJCV, etc. He is currently a student lead of the ShapeNet team. He has served as the chair of multiple international conferences and workshops (Co-chair of CVPR’15 workshop, Co-chair of ICCV’15 workshop, Co-chair of ECCV’16 workshop, Publication Chair of 3DVision'16, Program Chair of 3DVision'17). He is also an invited speaker at NIPS’16 workshop and 3DV'16 workshop on 3D deep learning.
Generation of 3D data by deep neural network has been attracting increasing attention in the research community. The majority of extant works resort to regular representations such as volumetric grids or collection of images; however, these representations obscure the natural invariance of 3D shapes under geometric transformations, and also suffer from a number of other issues. In this paper we address the problem of 3D reconstruction from a single image, generating a straight-forward form of output – point cloud coordinates. Along with this problem arises a unique and interesting issue, that the groundtruth shape for an input image may be ambiguous. Driven by this unorthodox output form and the inherent ambiguity in groundtruth, we design architecture, loss function and learning paradigm that are novel and effective. Our final solution is a conditional shape sampler, capable of predicting multiple plausible 3D point clouds from an input image. In experiments not only can our system outperform state-ofthe-art methods on single image based 3d reconstruction benchmarks; but it also shows strong performance for 3d shape completion and promising ability in making multiple plausible predictions.
Bio:
Hao Su is currently a Ph.D. candidate in the Computer Science Department of Stanford University. He is a member of Stanford AI Lab and Geometric Computing Lab. Hao’s research interests are broad, spanning computer vision, computer graphics, machine learning, and robotics. He is particularly interested in deep learning for 3D data understanding and interconnecting 3D data with other modalities such as images and texts. Hao has published papers at CVPR, ICCV, NIPS, ICML, SIGGRAPH, SIGGRAPH Asia, VLDB, SIGSPATIAL, IJCV, etc. He is currently a student lead of the ShapeNet team. He has served as the chair of multiple international conferences and workshops (Co-chair of CVPR’15 workshop, Co-chair of ICCV’15 workshop, Co-chair of ECCV’16 workshop, Publication Chair of 3DVision'16, Program Chair of 3DVision'17). He is also an invited speaker at NIPS’16 workshop and 3DV'16 workshop on 3D deep learning.