mlsanityData to 14 Oct 2026

Neural Radiosity

arXiv 2105.12319 ↗First posted 26 May 2021cs.GR cs.AIcited by 33

Not on the map. Why?

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.

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

16 of 37 references.

References · 16

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
  3. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  4. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  5. 2020Neural Sparse Voxel Fieldscited by 959
  6. 2020Convolutional Occupancy Networkscited by 761
  7. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
  8. 2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
  9. 2020Local Implicit Grid Representations for 3D Scenescited by 373
  10. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  11. 2020Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstructioncited by 321
  12. 2020Learned Initializations for Optimizing Coordinate-Based Neural Representationscited by 242
4 more
  1. 2018Neural Importance Samplingcited by 155
  2. 2020Neural Control Variatescited by 34
  3. 2018Learning to Importance Sample in Primary Sample Spacecited by 9
  4. 2017Learning Light Transport the Reinforced Waycited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 4; 2024: 7; 2025: 11; 2026: 4.

33 papers.

Sort:

By area:

  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  2. 2021Neural Fields in Visual Computing and Beyondcited by 540
  3. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
  4. 2023NeISF: Neural Incident Stokes Field for Geometry and Material Estimationcited by 25
  5. 2025RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illuminationcited by 23
  6. 2022Interactive Volume Visualization via Multi-Resolution Hash Encoding based Neural Representationcited by 19
  7. 2023HyperINR: A Fast and Predictive Hypernetwork for Implicit Neural Representations via Knowledge Distillationcited by 19
  8. 2022Active Exploration for Neural Global Illumination of Variable Scenescited by 11
  9. 2023Inverse Global Illumination using a Neural Radiometric Priorcited by 9
  10. 2024NeISF++: Neural Incident Stokes Field for Polarized Inverse Rendering of Conductors and Dielectricscited by 9
  11. 2023Neural Free-Viewpoint Relighting for Glossy Indirect Illuminationcited by 7
  12. 2022ROAD: Learning an Implicit Recursive Octree Auto-Decoder to Efficiently Encode 3D Shapescited by 6
21 more
  1. 2025GSCache: Real-Time Radiance Caching for Volume Path Tracing using 3D Gaussian Splattingcited by 5
  2. 2024Neural Rendering and Its Hardware Acceleration: A Reviewcited by 4
  3. 2025Differentiable Light Transport with Gaussian Surfels via Adapted Radiosity for Efficient Relighting and Geometry Reconstructioncited by 4
  4. 2025How Learnable Grids Recover Fine Detail in Low Dimensions: A Neural Tangent Kernel Analysis of Multigrid Parametric Encodingscited by 3
  5. 2025F-Hash: Feature-Based Hash Design for Time-Varying Volume Visualization via Multi-Resolution Tesseract Encodingcited by 3
  6. 2025Vertex Features for Neural Global Illuminationcited by 3
  7. 2024ESR-NeRF: Emissive Source Reconstruction Using LDR Multi-view Imagescited by 2
  8. 2025Beyond Reconstruction: A Physics Based Neural Deferred Shader for Photo-realistic Renderingcited by 2
  9. 2026Radiometrically Consistent Gaussian Surfels for Inverse Renderingcited by 2
  10. 2022Differentiable Neural Radiositycited by 1
  11. 2024Physics informed cell representations for variational formulation of multiscale problemscited by 1
  12. 2025Neural Cone Radiosity for Interactive Global Illumination with Glossy Materialscited by 1
  13. 2024Fully-fused Multi-Layer Perceptrons on Intel Data Center GPUscited by 0
  14. 2024Probabilistic Directed Distance Fields for Ray-Based Shape Representationscited by 0
  15. 2024Fast and Accurate Neural Rendering Using Semi-Gradientscited by 0
  16. 2025Geometry-Aware Global Feature Aggregation for Real-Time Indirect Illuminationcited by 0
  17. 2025Geometric Integration for Neural Control Variatescited by 0
  18. 2025GLOW: Global Illumination-Aware Inverse Rendering of Indoor Scenes Captured with Dynamic Co-Located Light & Cameracited by 0
  19. 2026Rotated Lights for Consistent and Efficient 2D Gaussians Inverse Renderingcited by 0
  20. 2026RenderFormer++: Scalable and Physics-Informed Feed-Forward Neural Renderingcited by 0
  21. 2026PanoLess: Environment Reconstruction from Partial Reflective Viewscited by 0