Differentiable Voxelization and Mesh Morphing
2024-07-15Code Available2· sign in to hype
Yihao Luo, Yikai Wang, Zhengrui Xiang, Yuliang Xiu, Guang Yang, ChoonHwai Yap
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/luo-yihao/dophOfficialIn paperpytorch★ 93
- github.com/luo-yihao/ghdheartOfficialIn paperpytorch★ 34
Abstract
In this paper, we propose the differentiable voxelization of 3D meshes via the winding number and solid angles. The proposed approach achieves fast, flexible, and accurate voxelization of 3D meshes, admitting the computation of gradients with respect to the input mesh and GPU acceleration. We further demonstrate the application of the proposed voxelization in mesh morphing, where the voxelized mesh is deformed by a neural network. The proposed method is evaluated on the ShapeNet dataset and achieves state-of-the-art performance in terms of both accuracy and efficiency.