English

Voxel Deformation-Aware Neural Intersection Function

Graphics 2026-04-28 v1

Abstract

We extend the Locally-Subdivided Neural Intersection Function (LSNIF) to support parameterized deformable and animated geometry. Our approach introduces a rest-space and deformed-space formulation inspired by meshless rendering, allowing ray samples to be mapped back to a canonical space where a single neural network represents geometry consistently across poses without retraining. To maintain accuracy under deformation-aware training, we incorporate scale-invariant distance regression, uncertainty-weighted multi-task learning, and a hybrid positional-grid encoding. The resulting method preserves the compactness and efficiency of LSNIF while enabling robust neural intersection prediction for dynamic geometry.

Keywords

Cite

@article{arxiv.2604.24666,
  title  = {Voxel Deformation-Aware Neural Intersection Function},
  author = {Chih-Chen Kao and Grzegorz Makowski and Shin Fujieda and Takahiro Harada},
  journal= {arXiv preprint arXiv:2604.24666},
  year   = {2026}
}
R2 v1 2026-07-01T12:37:33.554Z