# Fast Local Neural Regression for Low-Cost, Path Traced Lambertian Global Illumination

arXiv: https://arxiv.org/abs/2410.11625 · HTML: https://mlsanity.com/paper/2410.11625/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 37 references that are in the map.
- First posted on arXiv 15 Oct 2024.

## Builds on (most cited first, 6 of 6)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Real-time Neural Radiance Caching for Path Tracing](https://mlsanity.com/paper/2106.12372/) (2021)
- [Enhancing Photorealism Enhancement](https://mlsanity.com/paper/2105.04619/) (2021)
- [Fast Guided Filter](https://mlsanity.com/paper/1505.00996/) (2015)
- [High-Quality Real-Time Rendering Using Subpixel Sampling Reconstruction](https://mlsanity.com/paper/2301.01036/) (2023)
- [Generative Adversarial Shaders for Real-Time Realism Enhancement](https://mlsanity.com/paper/2306.04629/) (2023)

## Abstract (arXiv)

Despite recent advances in hardware acceleration of ray tracing, real-time ray budgets remain stubbornly limited at a handful of samples per pixel (spp) on commodity hardware, placing the onus on denoising algorithms to achieve high visual quality for path traced global illumination. Neural network-based solutions give excellent result quality at the cost of increased execution time relative to hand-engineered methods, making them less suitable for deployment on resource-constrained systems. We therefore propose incorporating a neural network into a computationally-efficient local linear model-based denoiser, and demonstrate faithful single-frame reconstruction of global illumination for Lambertian scenes at very low sample counts (1spp) and for low computational cost. Other contributions include improving the quality and performance of local linear model-based denoising through a simplified mathematical treatment, and demonstration of the surprising usefulness of ambient occlusion as a guide channel. We also show how our technique is straightforwardly extensible to joint denoising and upsampling of path traced renders with reference to low-cost, rasterized guide channels.