Direct structure estimation for 3D reconstruction

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 structur...

Full description

Saved in:
Bibliographic Details
Main Authors: JIANG, Nianjuan, LIN, Wen-yan, DO, Minh N., LU, Jiangbo
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2015
Subjects:
Online Access:https://ink.library.smu.edu.sg/sis_research/4808
https://ink.library.smu.edu.sg/context/sis_research/article/5811/viewcontent/Jiang_Direct_Structure_Estimation_2015_CVPR_paper.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
id sg-smu-ink.sis_research-5811
record_format dspace
spelling sg-smu-ink.sis_research-58112020-01-16T10:03:54Z Direct structure estimation for 3D reconstruction JIANG, Nianjuan LIN, Wen-yan DO, Minh N. LU, Jiangbo 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. 2015-06-12T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/4808 info:doi/10.1109/CVPR.2015.7298881 https://ink.library.smu.edu.sg/context/sis_research/article/5811/viewcontent/Jiang_Direct_Structure_Estimation_2015_CVPR_paper.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Computer and Systems Architecture
institution Singapore Management University
building SMU Libraries
continent Asia
country Singapore
Singapore
content_provider SMU Libraries
collection InK@SMU
language English
topic Computer and Systems Architecture
spellingShingle Computer and Systems Architecture
JIANG, Nianjuan
LIN, Wen-yan
DO, Minh N.
LU, Jiangbo
Direct structure estimation for 3D reconstruction
description 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.
format text
author JIANG, Nianjuan
LIN, Wen-yan
DO, Minh N.
LU, Jiangbo
author_facet JIANG, Nianjuan
LIN, Wen-yan
DO, Minh N.
LU, Jiangbo
author_sort JIANG, Nianjuan
title Direct structure estimation for 3D reconstruction
title_short Direct structure estimation for 3D reconstruction
title_full Direct structure estimation for 3D reconstruction
title_fullStr Direct structure estimation for 3D reconstruction
title_full_unstemmed Direct structure estimation for 3D reconstruction
title_sort direct structure estimation for 3d reconstruction
publisher Institutional Knowledge at Singapore Management University
publishDate 2015
url https://ink.library.smu.edu.sg/sis_research/4808
https://ink.library.smu.edu.sg/context/sis_research/article/5811/viewcontent/Jiang_Direct_Structure_Estimation_2015_CVPR_paper.pdf
_version_ 1770575052185534464