Differentiable Voxelization and Mesh Morphing
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 7 of its 20 references that are in the map. First posted on arXiv 15 Jul 2024.
Builds on
7 of 20 references.
References · 7
- 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
- 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
- 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
- 2016Generative and Discriminative Voxel Modeling with Convolutional Neural Networkscited by 128
- 2020Differentiable Rendering: A Surveycited by 123
- 2022Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representationscited by 71
- 2016Boolean Operations using Generalized Winding Numberscited by 1
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.