3D shape reconstruction with a multiple-constraint estimation approach
In this study, a multiple-constraint estimation algorithm is presented to estimate the 3D shape of a 2D image sequence. Given the training data, a sparse representation model with an elastic net, i.e., l1−norm and l2−norm constraints, is devised to extract the shape bases. In the sparse model, the l...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-05-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnins.2023.1191574/full |
| _version_ | 1797823714886156288 |
|---|---|
| author | Xia Chen Xia Chen Xia Chen Zhan-Li Sun Zhan-Li Sun Ying Zhang |
| author_facet | Xia Chen Xia Chen Xia Chen Zhan-Li Sun Zhan-Li Sun Ying Zhang |
| author_sort | Xia Chen |
| collection | DOAJ |
| description | In this study, a multiple-constraint estimation algorithm is presented to estimate the 3D shape of a 2D image sequence. Given the training data, a sparse representation model with an elastic net, i.e., l1−norm and l2−norm constraints, is devised to extract the shape bases. In the sparse model, the l1−norm and l2−norm constraints are enforced to regulate the sparsity and scale of coefficients, respectively. After obtaining the shape bases, a penalized least-square model is formulated to estimate 3D shape and motion, by considering the orthogonal constraint of the transformation matrix, and the similarity constraint between the 2D observations and the shape bases. Moreover, an Augmented Lagrange Multipliers (ALM) iterative algorithm is adopted to solve the optimization of the proposed approach. Experimental results on the well-known CMU image sequences demonstrate the effectiveness and feasibility of the proposed model. |
| first_indexed | 2024-03-13T10:28:05Z |
| format | Article |
| id | doaj.art-91caa9877f8a47c8b22df50fd0a13bad |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-03-13T10:28:05Z |
| publishDate | 2023-05-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-91caa9877f8a47c8b22df50fd0a13bad2023-05-19T04:51:54ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2023-05-011710.3389/fnins.2023.119157411915743D shape reconstruction with a multiple-constraint estimation approachXia Chen0Xia Chen1Xia Chen2Zhan-Li Sun3Zhan-Li Sun4Ying Zhang5School of Information and Computer, Anhui Agricultural University, Hefei, ChinaKey Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Institute of Physical Science and Information Technology, Anhui University, Hefei, ChinaAnhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, ChinaSchool of Electrical Engineering and Automation, Anhui University, Hefei, ChinaInformation Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei, ChinaSchool of Electrical Engineering and Automation, Anhui University, Hefei, ChinaIn this study, a multiple-constraint estimation algorithm is presented to estimate the 3D shape of a 2D image sequence. Given the training data, a sparse representation model with an elastic net, i.e., l1−norm and l2−norm constraints, is devised to extract the shape bases. In the sparse model, the l1−norm and l2−norm constraints are enforced to regulate the sparsity and scale of coefficients, respectively. After obtaining the shape bases, a penalized least-square model is formulated to estimate 3D shape and motion, by considering the orthogonal constraint of the transformation matrix, and the similarity constraint between the 2D observations and the shape bases. Moreover, an Augmented Lagrange Multipliers (ALM) iterative algorithm is adopted to solve the optimization of the proposed approach. Experimental results on the well-known CMU image sequences demonstrate the effectiveness and feasibility of the proposed model.https://www.frontiersin.org/articles/10.3389/fnins.2023.1191574/fullnon-rigid structure from motionelastic netsimilarity constraintAugmented Lagrange multipliers3D reconstruction |
| spellingShingle | Xia Chen Xia Chen Xia Chen Zhan-Li Sun Zhan-Li Sun Ying Zhang 3D shape reconstruction with a multiple-constraint estimation approach Frontiers in Neuroscience non-rigid structure from motion elastic net similarity constraint Augmented Lagrange multipliers 3D reconstruction |
| title | 3D shape reconstruction with a multiple-constraint estimation approach |
| title_full | 3D shape reconstruction with a multiple-constraint estimation approach |
| title_fullStr | 3D shape reconstruction with a multiple-constraint estimation approach |
| title_full_unstemmed | 3D shape reconstruction with a multiple-constraint estimation approach |
| title_short | 3D shape reconstruction with a multiple-constraint estimation approach |
| title_sort | 3d shape reconstruction with a multiple constraint estimation approach |
| topic | non-rigid structure from motion elastic net similarity constraint Augmented Lagrange multipliers 3D reconstruction |
| url | https://www.frontiersin.org/articles/10.3389/fnins.2023.1191574/full |
| work_keys_str_mv | AT xiachen 3dshapereconstructionwithamultipleconstraintestimationapproach AT xiachen 3dshapereconstructionwithamultipleconstraintestimationapproach AT xiachen 3dshapereconstructionwithamultipleconstraintestimationapproach AT zhanlisun 3dshapereconstructionwithamultipleconstraintestimationapproach AT zhanlisun 3dshapereconstructionwithamultipleconstraintestimationapproach AT yingzhang 3dshapereconstructionwithamultipleconstraintestimationapproach |