Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

DynoSurf: Neural Deformation-based Temporally Consistent Dynamic Surface Reconstruction

About

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.

Yuxin Yao, Siyu Ren, Junhui Hou, Zhi Deng, Juyong Zhang, Wenping Wang• 2024

Related benchmarks

TaskDatasetResultRank
Dynamic Surface ReconstructionDFAUST (test)
Chamfer Distance (CD)2.13
6
Dynamic Surface ReconstructionDT4D (test)
Chamfer Distance (CD)15.18
6
Dynamic Surface ReconstructionAMA (test)
CD (10^-5)1.01
4
Showing 3 of 3 rows

Other info

Follow for update