# Neural Radiosity

arXiv: https://arxiv.org/abs/2105.12319 · HTML: https://mlsanity.com/paper/2105.12319/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 26 May 2021.

## Builds on (most cited first, 16 of 16)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Neural Sparse Voxel Fields](https://mlsanity.com/paper/2007.11571/) (2020)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes](https://mlsanity.com/paper/2011.13084/) (2020)
- [Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes](https://mlsanity.com/paper/2101.10994/) (2021)
- [Local Implicit Grid Representations for 3D Scenes](https://mlsanity.com/paper/2003.08981/) (2020)
- [Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion](https://mlsanity.com/paper/2003.01456/) (2020)
- [Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction](https://mlsanity.com/paper/2003.10983/) (2020)
- [Learned Initializations for Optimizing Coordinate-Based Neural Representations](https://mlsanity.com/paper/2012.02189/) (2020)
- [Neural Importance Sampling](https://mlsanity.com/paper/1808.03856/) (2018)
- [Neural Control Variates](https://mlsanity.com/paper/2006.01524/) (2020)
- [Learning to Importance Sample in Primary Sample Space](https://mlsanity.com/paper/1808.07840/) (2018)
- [Learning Light Transport the Reinforced Way](https://mlsanity.com/paper/1701.07403/) (2017)

## Built on by (most cited first, 30 of 33)

- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction](https://mlsanity.com/paper/2206.00665/) (2022)
- [NeISF: Neural Incident Stokes Field for Geometry and Material Estimation](https://mlsanity.com/paper/2311.13187/) (2023)
- [RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination](https://mlsanity.com/paper/2505.21925/) (2025)
- [Interactive Volume Visualization via Multi-Resolution Hash Encoding based Neural Representation](https://mlsanity.com/paper/2207.11620/) (2022)
- [HyperINR: A Fast and Predictive Hypernetwork for Implicit Neural Representations via Knowledge Distillation](https://mlsanity.com/paper/2304.04188/) (2023)
- [Active Exploration for Neural Global Illumination of Variable Scenes](https://mlsanity.com/paper/2203.08272/) (2022)
- [Inverse Global Illumination using a Neural Radiometric Prior](https://mlsanity.com/paper/2305.02192/) (2023)
- [NeISF++: Neural Incident Stokes Field for Polarized Inverse Rendering of Conductors and Dielectrics](https://mlsanity.com/paper/2411.10189/) (2024)
- [Neural Free-Viewpoint Relighting for Glossy Indirect Illumination](https://mlsanity.com/paper/2307.06335/) (2023)
- [ROAD: Learning an Implicit Recursive Octree Auto-Decoder to Efficiently Encode 3D Shapes](https://mlsanity.com/paper/2212.06193/) (2022)
- [GSCache: Real-Time Radiance Caching for Volume Path Tracing using 3D Gaussian Splatting](https://mlsanity.com/paper/2507.19718/) (2025)
- [Neural Rendering and Its Hardware Acceleration: A Review](https://mlsanity.com/paper/2402.00028/) (2024)
- [Differentiable Light Transport with Gaussian Surfels via Adapted Radiosity for Efficient Relighting and Geometry Reconstruction](https://mlsanity.com/paper/2509.18497/) (2025)
- [How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodings](https://mlsanity.com/paper/2504.13412/) (2025)
- [F-Hash: Feature-Based Hash Design for Time-Varying Volume Visualization via Multi-Resolution Tesseract Encoding](https://mlsanity.com/paper/2507.03836/) (2025)
- [Vertex Features for Neural Global Illumination](https://mlsanity.com/paper/2508.07852/) (2025)
- [ESR-NeRF: Emissive Source Reconstruction Using LDR Multi-view Images](https://mlsanity.com/paper/2404.15707/) (2024)
- [Beyond Reconstruction: A Physics Based Neural Deferred Shader for Photo-realistic Rendering](https://mlsanity.com/paper/2504.12273/) (2025)
- [Radiometrically Consistent Gaussian Surfels for Inverse Rendering](https://mlsanity.com/paper/2603.01491/) (2026)
- [Differentiable Neural Radiosity](https://mlsanity.com/paper/2201.13190/) (2022)
- [Physics informed cell representations for variational formulation of multiscale problems](https://mlsanity.com/paper/2405.16770/) (2024)
- [Neural Cone Radiosity for Interactive Global Illumination with Glossy Materials](https://mlsanity.com/paper/2509.07522/) (2025)
- [Fully-fused Multi-Layer Perceptrons on Intel Data Center GPUs](https://mlsanity.com/paper/2403.17607/) (2024)
- [Probabilistic Directed Distance Fields for Ray-Based Shape Representations](https://mlsanity.com/paper/2404.09081/) (2024)
- [Fast and Accurate Neural Rendering Using Semi-Gradients](https://mlsanity.com/paper/2410.10149/) (2024)
- [Geometry-Aware Global Feature Aggregation for Real-Time Indirect Illumination](https://mlsanity.com/paper/2508.08826/) (2025)
- [Geometric Integration for Neural Control Variates](https://mlsanity.com/paper/2509.15538/) (2025)
- [GLOW: Global Illumination-Aware Inverse Rendering of Indoor Scenes Captured with Dynamic Co-Located Light & Camera](https://mlsanity.com/paper/2511.22857/) (2025)

## Abstract (arXiv)

We introduce Neural Radiosity, an algorithm to solve the rendering equation by minimizing the norm of its residual similar as in traditional radiosity techniques. Traditional basis functions used in radiosity techniques, such as piecewise polynomials or meshless basis functions are typically limited to representing isotropic scattering from diffuse surfaces. Instead, we propose to leverage neural networks to represent the full four-dimensional radiance distribution, directly optimizing network parameters to minimize the norm of the residual. Our approach decouples solving the rendering equation from rendering (perspective) images similar as in traditional radiosity techniques, and allows us to efficiently synthesize arbitrary views of a scene. In addition, we propose a network architecture using geometric learnable features that improves convergence of our solver compared to previous techniques. Our approach leads to an algorithm that is simple to implement, and we demonstrate its effectiveness on a variety of scenes with non-diffuse surfaces.