Differentiable Voxelization and Mesh Morphing
This enables efficient mesh morphing for 3D computer vision applications, though it appears incremental as it builds on existing voxelization techniques.
The paper tackles the problem of differentiable voxelization of 3D meshes using winding numbers and solid angles, achieving state-of-the-art accuracy and efficiency on the ShapeNet dataset.
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.