MeshFeat: Multi-Resolution Features for Neural Fields on Meshes
This work addresses the need for faster neural field inference in computer graphics applications, such as object animation, but is incremental as it adapts existing multi-resolution grid ideas to meshes.
The authors tackled the problem of slow inference times in neural fields on meshes by proposing MeshFeat, a multi-resolution feature encoding tailored to meshes, which achieved significant speed-up while maintaining comparable reconstruction quality for tasks like texture reconstruction and BRDF representation.
Parametric feature grid encodings have gained significant attention as an encoding approach for neural fields since they allow for much smaller MLPs, which significantly decreases the inference time of the models. In this work, we propose MeshFeat, a parametric feature encoding tailored to meshes, for which we adapt the idea of multi-resolution feature grids from Euclidean space. We start from the structure provided by the given vertex topology and use a mesh simplification algorithm to construct a multi-resolution feature representation directly on the mesh. The approach allows the usage of small MLPs for neural fields on meshes, and we show a significant speed-up compared to previous representations while maintaining comparable reconstruction quality for texture reconstruction and BRDF representation. Given its intrinsic coupling to the vertices, the method is particularly well-suited for representations on deforming meshes, making it a good fit for object animation.