Saved in:
Bibliographic Details
Main Authors: Fujieda, Shin, Kao, Chih-Chen, Harada, Takahiro
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.21627
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918005417443328
author Fujieda, Shin
Kao, Chih-Chen
Harada, Takahiro
author_facet Fujieda, Shin
Kao, Chih-Chen
Harada, Takahiro
contents Neural representations have shown the potential to accelerate ray casting in a conventional ray-tracing-based rendering pipeline. We introduce a novel approach called Locally-Subdivided Neural Intersection Function (LSNIF) that replaces bottom-level BVHs used as traditional geometric representations with a neural network. Our method introduces a sparse hash grid encoding scheme incorporating geometry voxelization, a scene-agnostic training data collection, and a tailored loss function. It enables the network to output not only visibility but also hit-point information and material indices. LSNIF can be trained offline for a single object, allowing us to use LSNIF as a replacement for its corresponding BVH. With these designs, the network can handle hit-point queries from any arbitrary viewpoint, supporting all types of rays in the rendering pipeline. We demonstrate that LSNIF can render a variety of scenes, including real-world scenes designed for other path tracers, while achieving a memory footprint reduction of up to 106.2x compared to a compressed BVH.
format Preprint
id arxiv_https___arxiv_org_abs_2504_21627
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LSNIF: Locally-Subdivided Neural Intersection Function
Fujieda, Shin
Kao, Chih-Chen
Harada, Takahiro
Graphics
Neural representations have shown the potential to accelerate ray casting in a conventional ray-tracing-based rendering pipeline. We introduce a novel approach called Locally-Subdivided Neural Intersection Function (LSNIF) that replaces bottom-level BVHs used as traditional geometric representations with a neural network. Our method introduces a sparse hash grid encoding scheme incorporating geometry voxelization, a scene-agnostic training data collection, and a tailored loss function. It enables the network to output not only visibility but also hit-point information and material indices. LSNIF can be trained offline for a single object, allowing us to use LSNIF as a replacement for its corresponding BVH. With these designs, the network can handle hit-point queries from any arbitrary viewpoint, supporting all types of rays in the rendering pipeline. We demonstrate that LSNIF can render a variety of scenes, including real-world scenes designed for other path tracers, while achieving a memory footprint reduction of up to 106.2x compared to a compressed BVH.
title LSNIF: Locally-Subdivided Neural Intersection Function
topic Graphics
url https://arxiv.org/abs/2504.21627