Conference 3 Dec - 6 Dec Exhibition 4 Dec - 6 Dec

Attendees

    Technical Papers

    01 Full Conference1 - Full Conference One Day

     

     

    Data In, Surface Out

    Friday, 05 December

    11:00 - 12:45

    Sweet Osmanthus Hall


    Real-Time Shading-Based Refinement for Consumer Depth Cameras

    We present the first real-time method for refinement of depth data
    using shape-from-shading in general uncontrolled scenes. Per frame, our real-time algorithm takes raw noisy depth data and an aligned RGB image, and approximates the time-varying incident lighting, which is then used for geometry refinement.


    Chenglei Wu, Max-Planck-Institute for Informatics
    Michael Zollhöfer, University of Erlangen-Nuremberg
    Matthias Nießner, Stanford University
    Marc Stamminger, University of Erlangen-Nuremberg
    Shahram Izadi, Microsoft Research Cambridge
    Christian Theobalt, Max-Planck-Institute for Informatics

    Robust Surface Reconstruction via Dictionary Learning

    Reconstructing mesh from point cloud is formulated as a dictionary learning problem. The topology and vertices are iteratively refined guided by a novel optimization model, and experiments demonstrate that our method outperforms state-of-the-art in terms of accuracy, robustness to noise and outliers, geometric feature and detail preservation.


    Shiyao Xiong, University of Science and Technology of China
    Juyong Zhang, University of Science and Technology of China
    Jianmin Zheng, Nanyang Technological University
    Jianfei Cai, Nanyang Technological University
    Ligang Liu, University of Science and Technology of China

    Morfit: Interactive Surface Reconstruction from Incomplete Point Clouds with Curve-Driven Topology and Geometry Control

    We present an interactive technique, called "morfit'', for surface reconstruction from highly incomplete and sparse scans of 3D objects possessing sharp features.


    Kangxue Yin, Shenzhen Institute of Advanced Technologies
    Hui Huang, Shenzhen Institute of Advanced Technologies
    Hao Zhang, Simon Fraser University
    Minglun Gong, Memorial University of Newfoundland
    Daniel Cohen-Or, Tel Aviv University
    Baoquan Chen, Shenzhen Institute of Advanced Technologies

    Quality-driven Poisson-guided Autoscanning

    We present a quality-driven, Poisson-guided autonomous scanning method. The key idea is to analyze the quality of a tentative watertight iso-surface model extracted from a Poisson field and use the analysis to guide the next scanning iteration.


    Shihao Wu, Shenzhen Institute of Advanced Technologies
    Wei Sun, Shenzhen Institute of Advanced Technologies
    Pinxin Long, Shenzhen Institute of Advanced Technologies
    Hui Huang, Shenzhen Institute of Advanced Technologies
    Daniel Cohen-Or, Tel Aviv University
    Minglun Gong, Memorial University of Newfoundland
    Oliver Deussen, University of Konstanz
    Baoquan Chen, Shenzhen Institute of Advanced Technologies

    Back to Top
    Go Back