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.
@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}
}