PD-SDF: Dynamic Surface Reconstruction Based on Plane Decomposition for Single View RGB-D Videos
Jinwen Li, Weixing Xie, Junfeng Yao, Shaoqi Wu, Youhong Peng, Mengyuan Ge, Xiao Dong
Abstract
Surface reconstruction of dynamic scenes from single view videos is a challenging task due to the highly ill-posed and under-constrained nature. Existing single view reconstruction methods suffer from severe quality issues, such as surface distortion and mesh adherison. In this paper, we propose an efficient dynamic representation network, PD-SDF, which consists of a 4D motion field and a 3D geometry field. The explicit disentanglement of motion and geometry based on planar factorization guarantees the mesh consistency across frames. Specifically, to address the mesh adhesion problem, we design a depth-guided sampling strategy to focus on optimizing the SDF field near the object surface. Due to insufficient geometric cues, we design various regularization strategies to constrain smoothness and topological correcness of the scene geometry. Extensive experiments show that our method outperforms existing methods in both appearance and geometry reconstruction. The project page: https://pd-sdf.github.io/
BibTeX
@inproceedings{icassp2025_pdsdfdynamicsurf,
title = {PD-SDF: Dynamic Surface Reconstruction Based on Plane Decomposition for Single View RGB-D Videos},
author = {Jinwen Li and Weixing Xie and Junfeng Yao and Shaoqi Wu and Youhong Peng and Mengyuan Ge and Xiao Dong},
booktitle = {ICASSP 2025},
year = {2025}
}