This paper explores the problem of reconstructing temporally consistent surfaces from a 3D point cloud sequence without correspondence. To address this challenging task, we propose DynoSurf, an unsupervised learning framework integrating a template surface representation with a learnable deformation field. Specifically, we design a coarse-to-fine strategy for learning the template surface based on the deformable tetrahedron representation. Furthermore, we propose a learnable deformation representation based on the learnable control points and blending weights, which can deform the template surface non-rigidly while maintaining the consistency of the local shape. Experimental results demonstrate the significant superiority of DynoSurf over current state-of-the-art approaches, showcasing its potential as a powerful tool for dynamic mesh reconstruction. The code is publicly available at https://github.com/yaoyx689/DynoSurf.
@article{arxiv.2403.11586,
title = {DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstruction},
author = {Yuxin Yao and Siyu Ren and Junhui Hou and Zhi Deng and Juyong Zhang and Wenping Wang},
journal= {arXiv preprint arXiv:2403.11586},
year = {2024}
}