# Differentiable Voxelization and Mesh Morphing

arXiv: https://arxiv.org/abs/2407.11272 · HTML: https://mlsanity.com/paper/2407.11272/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 20 references that are in the map.
- First posted on arXiv 15 Jul 2024.

## Builds on (most cited first, 7 of 7)

- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [Generative and Discriminative Voxel Modeling with Convolutional Neural Networks](https://mlsanity.com/paper/1608.04236/) (2016)
- [Differentiable Rendering: A Survey](https://mlsanity.com/paper/2006.12057/) (2020)
- [Dual Octree Graph Networks for Learning Adaptive Volumetric Shape Representations](https://mlsanity.com/paper/2205.02825/) (2022)
- [Boolean Operations using Generalized Winding Numbers](https://mlsanity.com/paper/1601.07953/) (2016)

## Built on by (most cited first, 3 of 3)

- [Voxify3D: Pixel Art Meets Volumetric Rendering](https://mlsanity.com/paper/2512.07834/) (2025)
- [Relational Anatomical Supervision for Accurate 3D Multi-Chamber Cardiac Mesh Reconstruction](https://mlsanity.com/paper/2503.07874/) (2025)
- [Differentiable Voxelization of Surface Representations](https://mlsanity.com/paper/2608.15934/) (2026)

## 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.