Direct Structure Estimation for 3D Reconstruction

被引:0
作者
Jiang, Nianjuan [1 ]
Lin, Wen-Yan [1 ]
Do, Minh N. [2 ]
Lu, Jiangbo [1 ]
机构
[1] Adv Digital Sci Ctr, Singapore, Singapore
[2] Univ Illinois, Champaign, IL USA
来源
2015 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | 2015年
关键词
POINTS; MOTION; VIEWS;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Most conventional structure-from-motion (SFM) techniques require camera pose estimation before computing any scene structure. In this work we show that when combined with single/multiple homography estimation, the general Euclidean rigidity constraint provides a simple formulation for scene structure recovery without explicit camera pose computation. This direct structure estimation (DSE) opens a new way to design a SFM system that reverses the order of structure and motion estimation. We show that this alternative approach works well for recovering scene structure and camera poses from sideway motion given planar or general man-made scenes.
引用
收藏
页码:2655 / 2663
页数:9
相关论文
共 50 条
[41]   A survey on 3D hand pose estimation: Cameras, methods, and datasets [J].
Li, Rui ;
Liu, Zhenyu ;
Tan, Jianrong .
PATTERN RECOGNITION, 2019, 93 :251-272
[42]   3D Scene Geometry Estimation from 360° Imagery: A Survey [J].
da Silveira, Thiago L. T. ;
Pinto, Paulo G. L. ;
Murrugarra-Llerena, Jeffri ;
Jung, Claudio R. .
ACM COMPUTING SURVEYS, 2023, 55 (04)
[43]   Model-based head tracking and 3D pose estimation [J].
Prêteux, F ;
Malciu, M .
MATHEMATICAL MODELING AND ESTIMATION TECHNIQUES IN COMPUTER VISION, 1998, 3457 :94-108
[44]   Locally Connected Network for Monocular 3D Human Pose Estimation [J].
Ci, Hai ;
Ma, Xiaoxuan ;
Wang, Chunyu ;
Wang, Yizhou .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (03) :1429-1442
[45]   3D Scene Flow Estimation with a Piecewise Rigid Scene Model [J].
Vogel, Christoph ;
Schindler, Konrad ;
Roth, Stefan .
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2015, 115 (01) :1-28
[46]   Dual-Path Transformer for 3D Human Pose Estimation [J].
Zhou, Lu ;
Chen, Yingying ;
Wang, Jinqiao .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2024, 34 (05) :3260-3270
[47]   On the Effect of Temporal Information on Monocular 3D Human Pose Estimation [J].
Brauer, Juergen ;
Gong, Wenjuan ;
Gonzalez, Jordi ;
Arens, Michael .
2011 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCV WORKSHOPS), 2011,
[48]   A Review of 3D Pose Estimation from a Monocular Image Sequence [J].
Shan Gan-lin ;
Ji Bing ;
Zhou Yun-feng .
PROCEEDINGS OF THE 2009 2ND INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, VOLS 1-9, 2009, :1946-1950
[49]   Real-Time 3D Eye Performance Reconstruction for RGBD Cameras [J].
Wen, Quan ;
Xu, Feng ;
Yong, Jun-Hai .
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2017, 23 (12) :2586-2598
[50]   3D shape reconstruction of moving object by tracking the sparse singular points [J].
Ebrahimnezhad, Hossein ;
Ghassemian, Hassan .
2006 IEEE WORKSHOP ON MULTIMEDIA SIGNAL PROCESSING, 2006, :192-+