mlsanityData to 7 Oct 2026

Deep Shading: Convolutional Neural Networks for Screen-Space Shading

arXiv 1603.06078 ↗First posted 19 Mar 2016cs.GR cs.LGcited by 46

Not on the map. Why?

Abstract (arXiv)

In computer vision, convolutional neural networks (CNNs) have recently achieved new levels of performance for several inverse problems where RGB pixel appearance is mapped to attributes such as positions, normals or reflectance. In computer graphics, screen-space shading has recently increased the visual quality in interactive image synthesis, where per-pixel attributes such as positions, normals or reflectance of a virtual 3D scene are converted into RGB pixel appearance, enabling effects like ambient occlusion, indirect light, scattering, depth-of-field, motion blur, or anti-aliasing. In this paper we consider the diagonal problem: synthesizing appearance from given per-pixel attributes using a CNN. The resulting Deep Shading simulates various screen-space effects at competitive quality and speed while not being programmed by human experts but learned from example images.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 6; 2023: 8; 2024: 3; 2025: 7; 2026: 12.

46 papers.

Sort:

By area:

  1. 2021FastNeRF: High-Fidelity Neural Rendering at 200FPScited by 510
  2. 2024RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion modelscited by 159
  3. 2021Real-time Neural Radiance Caching for Path Tracingcited by 91
  4. 2021Enhancing Photorealism Enhancementcited by 74
  5. 2025DiffusionRenderer: Neural Inverse and Forward Rendering with Video Diffusion Modelscited by 55
  6. 2022BokehMe: When Neural Rendering Meets Classical Renderingcited by 48
  7. 2023Relighting Neural Radiance Fields with Shadow and Highlight Hintscited by 41
  8. 2022OutCast: Outdoor Single-image Relighting with Cast Shadowscited by 30
  9. 2025Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Renderingcited by 16
  10. 2021NeuMIP: Multi-Resolution Neural Materialscited by 15
  11. 2022Active Exploration for Neural Global Illumination of Variable Scenescited by 11
  12. 2022Plateau-reduced Differentiable Path Tracingcited by 10
34 more
  1. 2023Inverse Rendering of Translucent Objects using Physical and Neural Rendererscited by 9
  2. 2026Generative World Renderercited by 8
  3. 2021DeRenderNet: Intrinsic Image Decomposition of Urban Scenes with Shape-(In)dependent Shading Renderingcited by 6
  4. 2022Photo-realistic Neural Domain Randomizationcited by 5
  5. 2023Zero Grads: Learning Local Surrogate Losses for Non-Differentiable Graphicscited by 5
  6. 2023Light Sampling Field and BRDF Representation for Physically-based Neural Renderingcited by 4
  7. 2024Neural Rendering and Its Hardware Acceleration: A Reviewcited by 4
  8. 2021Z2P: Instant Visualization of Point Cloudscited by 3
  9. 2022Bokeh-Loss GAN: Multi-Stage Adversarial Training for Realistic Edge-Aware Bokehcited by 3
  10. 2023Deep and Fast Approximate Order Independent Transparencycited by 3
  11. 2025Teamwork: Collaborative Diffusion with Low-rank Coordination and Adaptationcited by 3
  12. 2026Generative World Renderer at the Speed of Playcited by 3
  13. 2025A Generalizable Light Transport 3D Embedding for Global Illuminationcited by 2
  14. 2026RenderFlow: Single-Step Neural Rendering via Flow Matchingcited by 2
  15. 2021Neural BRDFs: Representation and Operationscited by 1
  16. 2023Generative Adversarial Shaders for Real-Time Realism Enhancementcited by 1
  17. 2025Neural Cone Radiosity for Interactive Global Illumination with Glossy Materialscited by 1
  18. 2026Three-dimensional visualization of X-ray micro-CT with large-scale datasets: Efficiency and accuracy for real-time interactioncited by 1
  19. 2026HorizonRelight: Relighting Long-horizon Videos Consistently via Diffusion Transformerscited by 1
  20. 2026RGBX-Next: Towards Realistic Generative Rendering from G-Bufferscited by 1
  21. 2021Learning from Shader Program Tracescited by 0
  22. 2021Sparse deep computer-generated holography for optical microscopycited by 0
  23. 2021N-SfC: Robust and Fast Shape Estimation from Caustic Imagescited by 0
  24. 2023GBSD: Generative Bokeh with Stage Diffusioncited by 0
  25. 2023A Tool for the Procedural Generation of Shaders using Interactive Evolutionary Algorithmscited by 0
  26. 2024A real-time rendering method for high albedo anisotropic materials with multiple scatteringcited by 0
  27. 2025Geometry-Aware Global Feature Aggregation for Real-Time Indirect Illuminationcited by 0
  28. 2025Neural Bloom: A Deep Learning Approach to Real-Time Lightingcited by 0
  29. 2026Lightweight Real-Time Rendering Parameter Optimization via XGBoost-Driven Lookup Tablescited by 0
  30. 2026OctaOctree Neural Radiosity for Real-time Glossy Material Renderingcited by 0
  31. 2026STAR-NT: Spatiotemporal Acceleration of Real-Time Neural Transparency Renderingcited by 0
  32. 2026Occlusion-Point Reuse for Ray-Traced Ambient Occlusion and Shadowcited by 0
  33. 2026RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitivescited by 0
  34. 2026DiffusionShadow: Diffusion-based Shadow Caching for Neural Volume Renderingcited by 0