Volumetric Performance Capture from Minimal Camera Viewpoints

被引:23
作者
Gilbert, Andrew [1 ]
Volino, Marco [1 ]
Collomosse, John [1 ,2 ]
Hilton, Adrian [1 ]
机构
[1] Univ Surrey, Ctr Vis Speech & Signal Proc, Guildford, Surrey, England
[2] Adobe Res, Creat Intelligence Lab, San Jose, CA USA
来源
COMPUTER VISION - ECCV 2018, PT XI | 2018年 / 11215卷
基金
“创新英国”项目; 英国工程与自然科学研究理事会;
关键词
Multi-view reconstruction; Deep autoencoders; Visual hull;
D O I
10.1007/978-3-030-01252-6_35
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We present a convolutional autoencoder that enables high fidelity volumetric reconstructions of human performance to be captured from multi-view video comprising only a small set of camera views. Our method yields similar end-to-end reconstruction error to that of a probabilistic visual hull computed using significantly more (double or more) viewpoints. We use a deep prior implicitly learned by the autoencoder trained over a dataset of view-ablated multi-view video footage of a wide range of subjects and actions. This opens up the possibility of high-end volumetric performance capture in on-set and prosumer scenarios where time or cost prohibit a high witness camera count.
引用
收藏
页码:591 / 607
页数:17
相关论文
共 32 条
  • [1] Multifocus structured illumination microscopy for fast volumetric super-resolution imaging
    Abrahamsson, Sara
    Blom, Hans
    Agostinho, Ana
    Jans, Daniel C.
    Jost, Aurelie
    Mueller, Marcel
    Nilsson, Linnea
    Bernhem, Kristoffer
    Lambert, Talley J.
    Heintzmann, Rainer
    Brismar, Hjalmar
    [J]. BIOMEDICAL OPTICS EXPRESS, 2017, 8 (09): : 4135 - 4140
  • [2] [Anonymous], 2012, CoRR
  • [3] [Anonymous], 2012, NEURIPS 2012
  • [4] Aydin V., 2017, ARXIV170505745V1
  • [5] Global Non-rigid Alignment of Surface Sequences
    Budd, Chris
    Huang, Peng
    Klaudiny, Martin
    Hilton, Adrian
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2013, 102 (1-3) : 256 - 270
  • [6] High-Quality Streamable Free-Viewpoint Video
    Collet, Alvaro
    Chuang, Ming
    Sweeney, Pat
    Gillett, Don
    Evseev, Dennis
    Calabrese, David
    Hoppe, Hugues
    Kirk, Adam
    Sullivan, Steve
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2015, 34 (04):
  • [7] Image Super-Resolution Using Deep Convolutional Networks
    Dong, Chao
    Loy, Chen Change
    He, Kaiming
    Tang, Xiaoou
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (02) : 295 - 307
  • [8] Fattal R, 2007, ACM T GRAPHIC, V26, DOI [10.1145/1276377.1276496, 10.1145/1239451.1239546]
  • [9] Franco J., 2003, P BRIT MACH VIS C BM
  • [10] Grauman K, 2003, PROC CVPR IEEE, P187