A Benchmark and Evaluation of Non-Rigid Structure from Motion

被引:14
作者
Jensen, Sebastian Hoppe Nesgaard [1 ]
Doest, Mads Emil Brix [1 ]
Aanaes, Henrik [1 ]
Del Bue, Alessio [2 ]
机构
[1] DTU Compute, Lyngby, Denmark
[2] Ist Italiano Tecnol IIT, Visual Geometry & Modelling VGM Lab, Pattern Anal & Comp Vis PAVIS, I-08028 Genoa, Italy
关键词
Non-rigid structure from motion; Dataset; Evaluation; Deformation modelling; 3D SHAPE; TRACKING; RECONSTRUCTION; FACTORIZATION;
D O I
10.1007/s11263-020-01406-y
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Non-rigid structure from motion (nrsfm), is a long standing and central problem in computer vision and its solution is necessary for obtaining 3D information from multiple images when the scene is dynamic. A main issue regarding the further development of this important computer vision topic, is the lack of high quality data sets. We here address this issue by presenting a data set created for this purpose, which is made publicly available, and considerably larger than the previous state of the art. To validate the applicability of this data set, and provide an investigation into the state of the art of nrsfm, including potential directions forward, we here present a benchmark and a scrupulous evaluation using this data set. This benchmark evaluates 18 different methods with available code that reasonably spans the state of the art in sparse nrsfm. This new public data set and evaluation protocol will provide benchmark tools for further development in this challenging field.
引用
收藏
页码:882 / 899
页数:18
相关论文
共 82 条
[1]   Large-Scale Data for Multiple-View Stereopsis [J].
Aanaes, Henrik ;
Jensen, Rasmus Ramsbol ;
Vogiatzis, George ;
Tola, Engin ;
Dahl, Anders Bjorholm .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2016, 120 (02) :153-168
[2]   A Comparative Study of Interest Point Performance on a Unique Data Set [J].
Aanaes, Henrik ;
Dahl, Anders Lindbjerg ;
Pedersen, Kim Steenstrup .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2012, 97 (01) :18-35
[3]   Force-Based Representation for Non-Rigid Shape and Elastic Model Estimation [J].
Agudo, Antonio ;
Moreno-Noguer, Francesc .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (09) :2137-2150
[4]   DUST: Dual Union of Spatio-Temporal Subspaces for Monocular Multiple Object 3D Reconstruction [J].
Agudo, Antonio ;
Moreno-Noguer, Francesc .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :1513-1521
[5]   Sequential Non-Rigid Structure from Motion Using Physical Priors [J].
Agudo, Antonio ;
Moreno-Noguer, Francesc ;
Calvo, Begona ;
Montiel, J. M. M. .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (05) :979-994
[6]   Bilinear Spatiotemporal Basis Models [J].
Akhter, Ijaz ;
Simon, Tomas ;
Khan, Sohaib ;
Matthews, Iain ;
Sheikh, Yaser .
ACM TRANSACTIONS ON GRAPHICS, 2012, 31 (02) :1-12
[7]   Trajectory Space: A Dual Representation for Nonrigid Structure from Motion [J].
Akhter, Ijaz ;
Sheikh, Yaser ;
Khan, Sohaib ;
Kanade, Takeo .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2011, 33 (07) :1442-1456
[8]  
[Anonymous], 2002, WORKSH VIS MOD DYN S
[9]  
[Anonymous], 2000, Multiple view geometry
[10]   Scalable Dense Monocular Surface Reconstruction [J].
Ansari, Mohammad Dawud ;
Golyani, Vladislav ;
Stricker, Didier .
PROCEEDINGS 2017 INTERNATIONAL CONFERENCE ON 3D VISION (3DV), 2017, :78-87