# Vertex Features for Neural Global Illumination

arXiv: https://arxiv.org/abs/2508.07852 · HTML: https://mlsanity.com/paper/2508.07852/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Builds on (most cited first, 19 of 19)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [K-Planes: Explicit Radiance Fields in Space, Time, and Appearance](https://mlsanity.com/paper/2301.10241/) (2023)
- [HexPlane: A Fast Representation for Dynamic Scenes](https://mlsanity.com/paper/2301.09632/) (2023)
- [Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes](https://mlsanity.com/paper/2101.10994/) (2021)
- [Neural Importance Sampling](https://mlsanity.com/paper/1808.03856/) (2018)
- [Variable Bitrate Neural Fields](https://mlsanity.com/paper/2206.07707/) (2022)
- [Stochastic Optimization with Importance Sampling](https://mlsanity.com/paper/1401.2753/) (2014)
- [Real-time Neural Radiance Caching for Path Tracing](https://mlsanity.com/paper/2106.12372/) (2021)
- [Compressing Volumetric Radiance Fields to 1 MB](https://mlsanity.com/paper/2211.16386/) (2022)
- [Neural Control Variates](https://mlsanity.com/paper/2006.01524/) (2020)
- [Neural Radiosity](https://mlsanity.com/paper/2105.12319/) (2021)
- [Compact Neural Graphics Primitives with Learned Hash Probing](https://mlsanity.com/paper/2312.17241/) (2023)
- [Active Exploration for Neural Global Illumination of Variable Scenes](https://mlsanity.com/paper/2203.08272/) (2022)
- [FuseSR: Super Resolution for Real-time Rendering through Efficient Multi-resolution Fusion](https://mlsanity.com/paper/2310.09726/) (2023)
- [Neural Parametric Mixtures for Path Guiding](https://mlsanity.com/paper/2504.04315/) (2025)
- [Online Neural Path Guiding with Normalized Anisotropic Spherical Gaussians](https://mlsanity.com/paper/2303.08064/) (2023)
- [MeshFeat: Multi-Resolution Features for Neural Fields on Meshes](https://mlsanity.com/paper/2407.13592/) (2024)

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

- [Neural Harmonic Textures for High-Quality Primitive Based Neural Reconstruction](https://mlsanity.com/paper/2604.01204/) (2026)
- [Geometry-Aware Global Feature Aggregation for Real-Time Indirect Illumination](https://mlsanity.com/paper/2508.08826/) (2025)
- [OctaOctree Neural Radiosity for Real-time Glossy Material Rendering](https://mlsanity.com/paper/2606.08469/) (2026)

## Abstract (arXiv)

Recent research on learnable neural representations has been widely adopted in the field of 3D scene reconstruction and neural rendering applications. However, traditional feature grid representations often suffer from substantial memory footprint, posing a significant bottleneck for modern parallel computing hardware. In this paper, we present neural vertex features, a generalized formulation of learnable representation for neural rendering tasks involving explicit mesh surfaces. Instead of uniformly distributing neural features throughout 3D space, our method stores learnable features directly at mesh vertices, leveraging the underlying geometry as a compact and structured representation for neural processing. This not only optimizes memory efficiency, but also improves feature representation by aligning compactly with the surface using task-specific geometric priors. We validate our neural representation across diverse neural rendering tasks, with a specific emphasis on neural radiosity. Experimental results demonstrate that our method reduces memory consumption to only one-fifth (or even less) of grid-based representations, while maintaining comparable rendering quality and lowering inference overhead.