3D Shape Estimation with an Enhanced Sparse Representation Approach

Jia Xiang Wang; Zhan Li Sun; Zhi Gang Zeng; Kin Man Lam

doi:10.1109/LSP.2021.3104088

3D Shape Estimation with an Enhanced Sparse Representation Approach

Jia Xiang Wang, Zhan Li Sun, Zhi Gang Zeng, Kin Man Lam

The Hong Kong Polytechnic University

Research output: Journal article publication › Journal article › Academic research › peer-review

Abstract

In this paper, an enhanced sparse representation approach is proposed to estimate the 3D shapes of objects in 2D image sequences. In the proposed method, the unknown 3D shape is estimated via a two-stage scheme, namely the main 3D shape estimation stage and the compensatory 3D shape estimation stage. Moreover, a reweighted sparse representation model is constructed to extract the shape bases for each estimation stage. In the sparse model, a reweighted constraint is enforced to enhance the coefficient sparsity of the shape bases. Experimental results on the well-known CMU image sequences demonstrate the effectiveness and feasibility of the proposed approach.

Original language	English
Article number	9511830
Pages (from-to)	1685-1688
Number of pages	4
Journal	IEEE Signal Processing Letters
Volume	28
DOIs	https://doi.org/10.1109/LSP.2021.3104088
Publication status	Published - Aug 2021

Keywords

3D reconstruction
Non-rigid structure from motion
sparse representation model

ASJC Scopus subject areas

Signal Processing
Electrical and Electronic Engineering
Applied Mathematics

More information

10.1109/LSP.2021.3104088

Cite this

@article{119d90f173964730a32c4ef64f89ff5f,

title = "3D Shape Estimation with an Enhanced Sparse Representation Approach",

abstract = "In this paper, an enhanced sparse representation approach is proposed to estimate the 3D shapes of objects in 2D image sequences. In the proposed method, the unknown 3D shape is estimated via a two-stage scheme, namely the main 3D shape estimation stage and the compensatory 3D shape estimation stage. Moreover, a reweighted sparse representation model is constructed to extract the shape bases for each estimation stage. In the sparse model, a reweighted constraint is enforced to enhance the coefficient sparsity of the shape bases. Experimental results on the well-known CMU image sequences demonstrate the effectiveness and feasibility of the proposed approach.",

keywords = "3D reconstruction, Non-rigid structure from motion, sparse representation model",

author = "Wang, {Jia Xiang} and Sun, {Zhan Li} and Zeng, {Zhi Gang} and Lam, {Kin Man}",

note = "Funding Information: Manuscript received June 22, 2021; revised August 7, 2021; accepted August 7, 2021. Date of publication August 11, 2021; date of current version August 31, 2021. This work was supported by the National Natural Science Foundation of China under Grant 61972002, in part by the Open Project of Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University (No. MMC202004), and in part by the High-performance Computing Platform of Anhui University for providing computing resources. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Lu Gan. (Corresponding author: Zhan-Li Sun.) Jia-Xiang Wang and Zhan-Li Sun are with the School of Artificial Intelligence, Anhui University, Hefei 230000, China (e-mail: 1018979952@qq.com; zhlsun2006@126.com). Publisher Copyright: {\textcopyright} 1994-2012 IEEE.",

year = "2021",

month = aug,

doi = "10.1109/LSP.2021.3104088",

language = "English",

volume = "28",

pages = "1685--1688",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "IEEE",

}

TY - JOUR

T1 - 3D Shape Estimation with an Enhanced Sparse Representation Approach

AU - Wang, Jia Xiang

AU - Sun, Zhan Li

AU - Zeng, Zhi Gang

AU - Lam, Kin Man

N1 - Funding Information: Manuscript received June 22, 2021; revised August 7, 2021; accepted August 7, 2021. Date of publication August 11, 2021; date of current version August 31, 2021. This work was supported by the National Natural Science Foundation of China under Grant 61972002, in part by the Open Project of Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University (No. MMC202004), and in part by the High-performance Computing Platform of Anhui University for providing computing resources. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Lu Gan. (Corresponding author: Zhan-Li Sun.) Jia-Xiang Wang and Zhan-Li Sun are with the School of Artificial Intelligence, Anhui University, Hefei 230000, China (e-mail: 1018979952@qq.com; zhlsun2006@126.com). Publisher Copyright: © 1994-2012 IEEE.

PY - 2021/8

Y1 - 2021/8

N2 - In this paper, an enhanced sparse representation approach is proposed to estimate the 3D shapes of objects in 2D image sequences. In the proposed method, the unknown 3D shape is estimated via a two-stage scheme, namely the main 3D shape estimation stage and the compensatory 3D shape estimation stage. Moreover, a reweighted sparse representation model is constructed to extract the shape bases for each estimation stage. In the sparse model, a reweighted constraint is enforced to enhance the coefficient sparsity of the shape bases. Experimental results on the well-known CMU image sequences demonstrate the effectiveness and feasibility of the proposed approach.

AB - In this paper, an enhanced sparse representation approach is proposed to estimate the 3D shapes of objects in 2D image sequences. In the proposed method, the unknown 3D shape is estimated via a two-stage scheme, namely the main 3D shape estimation stage and the compensatory 3D shape estimation stage. Moreover, a reweighted sparse representation model is constructed to extract the shape bases for each estimation stage. In the sparse model, a reweighted constraint is enforced to enhance the coefficient sparsity of the shape bases. Experimental results on the well-known CMU image sequences demonstrate the effectiveness and feasibility of the proposed approach.

KW - 3D reconstruction

KW - Non-rigid structure from motion

KW - sparse representation model

UR - http://www.scopus.com/inward/record.url?scp=85114648123&partnerID=8YFLogxK

U2 - 10.1109/LSP.2021.3104088

DO - 10.1109/LSP.2021.3104088

M3 - Journal article

AN - SCOPUS:85114648123

SN - 1070-9908

VL - 28

SP - 1685

EP - 1688

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

M1 - 9511830

ER -

3D Shape Estimation with an Enhanced Sparse Representation Approach

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this