# Neural Intersection Function

arXiv: https://arxiv.org/abs/2306.07191 · HTML: https://mlsanity.com/paper/2306.07191/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2023.

## Built on by (most cited first, 3 of 3)

- [Neural Bounding](https://mlsanity.com/paper/2310.06822/) (2023)
- [Neural Two-Level Monte Carlo Real-Time Rendering](https://mlsanity.com/paper/2412.04634/) (2024)
- [Geometric Integration for Neural Control Variates](https://mlsanity.com/paper/2509.15538/) (2025)

## Abstract (arXiv)

The ray casting operation in the Monte Carlo ray tracing algorithm usually adopts a bounding volume hierarchy (BVH) to accelerate the process of finding intersections to evaluate visibility. However, its characteristics are irregular, with divergence in memory access and branch execution, so it cannot achieve maximum efficiency on GPUs. This paper proposes a novel Neural Intersection Function based on a multilayer perceptron whose core operation contains only dense matrix multiplication with predictable memory access. Our method is the first solution integrating the neural network-based approach and BVH-based ray tracing pipeline into one unified rendering framework. We can evaluate the visibility and occlusion of secondary rays without traversing the most irregular and time-consuming part of the BVH and thus accelerate ray casting. The experiments show the proposed method can reduce the secondary ray casting time for direct illumination by up to 35% compared to a BVH-based implementation and still preserve the image quality.