TY - JOUR
T1 - Temporally coherent completion of dynamic shapes
AU - Li, Hao
AU - Luo, Linjie
AU - Vlasic, Daniel
AU - Peers, Pieter
AU - Popović, Jovan
AU - Pauly, Mark
AU - Rusinkiewicz, Szymon
N1 - Copyright:
Copyright 2012 Elsevier B.V., All rights reserved.
PY - 2012/1
Y1 - 2012/1
N2 - We present a novel shape completion technique for creating temporally coherent watertight surfaces from real-time captured dynamic performances. Because of occlusions and low surface albedo, scanned mesh sequences typically exhibit large holes that persist over extended periods of time. Most conventional dynamic shape reconstruction techniques rely on template models or assume slow deformations in the input data. Our framework sidesteps these requirements and directly initializes shape completion with topology derived from the visual hull. To seal the holes with patches that are consistent with the subject's motion, we first minimize surface bending energies in each frame to ensure smooth transitions across hole boundaries. Temporally coherent dynamics of surface patches are obtained by unwarping all frames within a time window using accurate interframe correspondences. Aggregated surface samples are then filtered with a temporal visibility kernel that maximizes the use of nonoccluded surfaces. A key benefit of our shape completion strategy is that it does not rely on long-range correspondences or a template model. Consequently, our method does not suffer error accumulation typically introduced by noise, large deformations, and drastic topological changes.We illustrate the effectiveness of our method on several high-resolution scans of human performances captured with a state-of-theart multiview 3D acquisition system.
AB - We present a novel shape completion technique for creating temporally coherent watertight surfaces from real-time captured dynamic performances. Because of occlusions and low surface albedo, scanned mesh sequences typically exhibit large holes that persist over extended periods of time. Most conventional dynamic shape reconstruction techniques rely on template models or assume slow deformations in the input data. Our framework sidesteps these requirements and directly initializes shape completion with topology derived from the visual hull. To seal the holes with patches that are consistent with the subject's motion, we first minimize surface bending energies in each frame to ensure smooth transitions across hole boundaries. Temporally coherent dynamics of surface patches are obtained by unwarping all frames within a time window using accurate interframe correspondences. Aggregated surface samples are then filtered with a temporal visibility kernel that maximizes the use of nonoccluded surfaces. A key benefit of our shape completion strategy is that it does not rely on long-range correspondences or a template model. Consequently, our method does not suffer error accumulation typically introduced by noise, large deformations, and drastic topological changes.We illustrate the effectiveness of our method on several high-resolution scans of human performances captured with a state-of-theart multiview 3D acquisition system.
KW - 3D video
KW - Animation reconstruction
KW - Dynamic surface reconstruction
KW - Dynamicshape acquisition
KW - Nonrigid registration
KW - Shape completion
KW - Temporal coherence
KW - Visual hull
UR - http://www.scopus.com/inward/record.url?scp=84863251855&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84863251855&partnerID=8YFLogxK
U2 - 10.1145/2077341.2077343
DO - 10.1145/2077341.2077343
M3 - Article
AN - SCOPUS:84863251855
VL - 31
JO - ACM Transactions on Computer Systems
JF - ACM Transactions on Computer Systems
SN - 0730-0301
IS - 1
M1 - 2
ER -