mlsanityData to 7 Oct 2026

Fast Spatially-Varying Indoor Lighting Estimation

arXiv 1906.03799 ↗First posted 10 Jun 2019cs.CVcited by 72

Not on the map. Why?

Abstract (arXiv)

We propose a real-time method to estimate spatiallyvarying indoor lighting from a single RGB image. Given an image and a 2D location in that image, our CNN estimates a 5th order spherical harmonic representation of the lighting at the given location in less than 20ms on a laptop mobile graphics card. While existing approaches estimate a single, global lighting representation or require depth as input, our method reasons about local lighting without requiring any geometry information. We demonstrate, through quantitative experiments including a user study, that our results achieve lower lighting estimation errors and are preferred by users over the state-of-the-art. Our approach can be used directly for augmented reality applications, where a virtual object is relit realistically at any position in the scene in real-time.

Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 9; 2023: 18; 2024: 14; 2025: 13; 2026: 6.

72 papers.

Sort:

By area:

  1. 2021NeRF for Outdoor Scene Relightingcited by 114
  2. 2024Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agentscited by 91
  3. 2023Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenescited by 89
  4. 2021Learning Indoor Inverse Rendering with 3D Spatially-Varying Lightingcited by 82
  5. 2022Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracingcited by 78
  6. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  7. 2023DiffusionLight: Light Probes for Free by Painting a Chrome Ballcited by 63
  8. 2022Physically-Based Editing of Indoor Scene Lighting from a Single Imagecited by 62
  9. 2022IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenescited by 62
  10. 2022StyleLight: HDR Panorama Generation for Lighting Estimation and Editingcited by 59
  11. 2021TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformationscited by 48
  12. 2021Self-supervised Outdoor Scene Relightingcited by 48
38 more
  1. 2023I2-SDF: Intrinsic Indoor Scene Reconstruction and Editing via Raytracing in Neural SDFscited by 42
  2. 2022Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertioncited by 35
  3. 2023EverLight: Indoor-Outdoor Editable HDR Lighting Estimationcited by 32
  4. 2021GMLight: Lighting Estimation via Geometric Distribution Approximationcited by 28
  5. 2023Material Palette: Extraction of Materials from a Single Imagecited by 28
  6. 2024Photorealistic Object Insertion with Diffusion-Guided Inverse Renderingcited by 27
  7. 2022Multi-view Inverse Rendering for Large-scale Real-world Indoor Scenescited by 23
  8. 2025A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Visioncited by 23
  9. 2022ORCa: Glossy Objects as Radiance Field Camerascited by 20
  10. 2021Sparse Needlets for Lighting Estimation with Spherical Transport Losscited by 18
  11. 2024Latent Intrinsics Emerge from Training to Relightcited by 17
  12. 2024ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusioncited by 16
  13. 2025LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fieldscited by 16
  14. 2021Spatially-Varying Outdoor Lighting Estimation from Intrinsicscited by 14
  15. 2024ReCap: Better Gaussian Relighting with Cross-Environment Capturescited by 14
  16. 2025LuxDiT: Lighting Estimation with Video Diffusion Transformercited by 14
  17. 2023Accidental Light Probescited by 13
  18. 2024Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variationcited by 13
  19. 2022Editable Indoor Lighting Estimationcited by 12
  20. 2023MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimationcited by 12
  21. 2023Spatiotemporally Consistent HDR Indoor Lighting Estimationcited by 12
  22. 2021Lighting, Reflectance and Geometry Estimation from 360circ Panoramic Stereocited by 11
  23. 2023Intrinsic Harmonization for Illumination-Aware Compositingcited by 11
  24. 2023Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectancecited by 11
  25. 2025GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDRcited by 11
  26. 2025DiffusionLight-Turbo: Accelerated Light Probes for Free via Single-Pass Chrome Ball Inpaintingcited by 11
  27. 2025GCC: Generative Color Constancy via Diffusing a Color Checkercited by 8
  28. 2023Relit-NeuLF: Efficient Relighting and Novel View Synthesis via Neural 4D Light Fieldcited by 7
  29. 2022Deep Graph Learning for Spatially-Varying Indoor Lighting Predictioncited by 6
  30. 2021Xihe: A 3D Vision-based Lighting Estimation Framework for Mobile Augmented Realitycited by 5
  31. 2023A Real-time Method for Inserting Virtual Objects into Neural Radiance Fieldscited by 5
  32. 2023Virtual Home Staging: Inverse Rendering and Editing an Indoor Panorama under Natural Illuminationcited by 5
  33. 2023Towards a Perceptual Evaluation Framework for Lighting Estimationcited by 5
  34. 2025Spatiotemporally Consistent Indoor Lighting Estimation with Diffusion Priorscited by 5
  35. 2023Multi-Camera Lighting Estimation for Photorealistic Front-Facing Mobile Augmented Realitycited by 3
  36. 2023Local-to-Global Panorama Inpainting for Locale-Aware Indoor Lighting Predictioncited by 3
  37. 2024LightOctree: Lightweight 3D Spatially-Coherent Indoor Lighting Estimationcited by 3
  38. 2024MAIR++: Improving Multi-view Attention Inverse Rendering with Implicit Lighting Representationcited by 3

50 most cited of 72 All 72 (JSON)