3D shape reconstruction with a multiple-constraint estimation approach

Xia Chen; Zhan-Li Sun; Ying Zhang

doi:10.3389/fnins.2023.1191574

3D shape reconstruction with a multiple-constraint estimation approach

Front Neurosci. 2023 May 19:17:1191574. doi: 10.3389/fnins.2023.1191574. eCollection 2023.

Authors

Xia Chen^{1

2

3}, Zhan-Li Sun^{4

5}, Ying Zhang⁴

Affiliations

¹ School of Information and Computer, Anhui Agricultural University, Hefei, China.
² Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Institute of Physical Science and Information Technology, Anhui University, Hefei, China.
³ Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei, China.
⁴ School of Electrical Engineering and Automation, Anhui University, Hefei, China.
⁵ Information Materials and Intelligent Sensing Laboratory of Anhui Province, Anhui University, Hefei, China.

Abstract

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.

Keywords: 3D reconstruction; Augmented Lagrange multipliers; elastic net; non-rigid structure from motion; similarity constraint.

Grants and funding

This work was supported by the National Natural Science Foundation of China (No. 61972002), the University Natural Science Research Project of Anhui Province (No. KJ2021A0180), Natural Science Foundation of Anhui Agricultural University (No. K2148001), Research Talents Stable Project of Anhui Agricultural University (No. rc482004), Key Laboratory of Intelligent Computing & Signal Processing, Ministry of Education (Anhui University) (No. 2020A002), Anhui Provincial Key Laboratory of Multimodal Cognitive Computation (Anhui University) (No. MMC202004), and the Anhui Provincial Natural Science Foundation (No. 2108085MC96).