Voxel Deformation-Aware Neural Intersection Function

Simple item page
dc.contributor.authorKao, Chih-Chen
dc.contributor.authorMakowski, Grzegorz
dc.contributor.authorFujieda, Shin
dc.contributor.authorHarada, Takahiro
dc.date.accessioned2026-04-20T08:43:29Z
dc.date.available2026-04-20T08:43:29Z
dc.date.issued2026
dc.description.abstractWe 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.
dc.description.sectionheadersRendering Representations & GPU Pipelines
dc.description.seriesinformationEurographics 2026 - Short Papers
dc.identifier.doi10.2312/egs.20261026
dc.identifier.isbn978-3-03868-299-8
dc.identifier.issn2309-5059
dc.identifier.pages4 pages
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/egs20261026
dc.identifier.urihttps://doi.org/10.2312/egs.20261026
dc.publisherThe Eurographics Association
dc.rightsCC-BY-4.0
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectRay tracing
dc.subjectNeural networks
dc.titleVoxel Deformation-Aware Neural Intersection Function
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
egs20261026.pdf
Size:
3.99 MB
Format:
Adobe Portable Document Format
Download
Collections
EG 2026 - Short Papers