Skip to main content

PDE-Based 3D Surface Reconstruction from Multi-View 2D Images.

Zhu, Z., Iglesias, A., Zhou, L., You, L. and Zhang, J. J., 2022. PDE-Based 3D Surface Reconstruction from Multi-View 2D Images. Mathematics, 10 (4), 542.

Full text available as:

mathematics-10-00542-v2.pdf - Published Version
Available under License Creative Commons Attribution.


DOI: 10.3390/math10040542


Partial differential equation (PDE) based surfaces own a lot of advantages, compared to other types of 3D representation. For instance, fewer variables are required to represent the same 3D shape; the position, tangent, and even curvature continuity between PDE surface patches can be naturally maintained when certain conditions are satisfied, and the physics-based nature is also kept. Although some works applied implicit PDEs to 3D surface reconstruction from images, there is little work on exploiting the explicit solutions of PDE to this topic, which is more efficient and accurate. In this paper, we propose a new method to apply the explicit solutions of a fourth-order partial differential equation to surface reconstruction from multi-view images. The method includes two stages: point clouds data are extracted from multi-view images in the first stage, which is fol-lowed by PDE-based surface reconstruction from the obtained point clouds data. Our computational experiments show that the reconstructed PDE surfaces exhibit good quality and can recover the ground truth with high accuracy. A comparison between various solutions with different com-plexity to the fourth-order PDE is also made to demonstrate the power and flexibility of our proposed explicit PDE for surface reconstruction from images.

Item Type:Article
Additional Information:This article belongs to the Special Issue Computer Graphics, Image Processing and Artificial Intelligence
Uncontrolled Keywords:shape reconstruction; explicit fourth-order partial differential equation; point clouds reconstruction from multi-view images; point cloud parameterization
Group:Faculty of Media & Communication
ID Code:36697
Deposited By: Symplectic RT2
Deposited On:01 Mar 2022 14:43
Last Modified:14 Mar 2022 14:33


Downloads per month over past year

More statistics for this item...
Repository Staff Only -