mlsanityData to 7 Oct 2026

Deep Parametric Indoor Lighting Estimation

arXiv 1910.08812 ↗First posted 19 Oct 2019cs.CVcited by 82

Not on the map. Why?

Abstract (arXiv)

We present a method to estimate lighting from a single image of an indoor scene. Previous work has used an environment map representation that does not account for the localized nature of indoor lighting. Instead, we represent lighting as a set of discrete 3D lights with geometric and photometric parameters. We train a deep neural network to regress these parameters from a single image, on a dataset of environment maps annotated with depth. We propose a differentiable layer to convert these parameters to an environment map to compute our loss; this bypasses the challenge of establishing correspondences between estimated and ground truth lights. We demonstrate, via quantitative and qualitative evaluations, that our representation and training scheme lead to more accurate results compared to previous work, while allowing for more realistic 3D object compositing with spatially-varying lighting.

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 14; 2023: 22; 2024: 12; 2025: 17; 2026: 5.

82 papers.

Sort:

By area:

  1. 2021Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decompositioncited by 204
  2. 2021Learning Indoor Inverse Rendering with 3D Spatially-Varying Lightingcited by 82
  3. 2022Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracingcited by 78
  4. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  5. 2023DiffusionLight: Light Probes for Free by Painting a Chrome Ballcited by 63
  6. 2022Physically-Based Editing of Indoor Scene Lighting from a Single Imagecited by 62
  7. 2022IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenescited by 62
  8. 2022StyleLight: HDR Panorama Generation for Lighting Estimation and Editingcited by 59
  9. 2021DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderercited by 52
  10. 2021Free-viewpoint Indoor Neural Relighting from Multi-view Stereocited by 50
  11. 2023PanoDiffusion: 360-degree Panorama Outpainting via Diffusioncited by 50
  12. 2022Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creationcited by 47
38 more
  1. 2021Deep Learning for HDR Imaging: State-of-the-Art and Future Trendscited by 45
  2. 2022Deep Learning for Omnidirectional Vision: A Survey and New Perspectivescited by 38
  3. 2023HRDFuse: Monocular 360degDepth Estimation by Collaboratively Learning Holistic-with-Regional Depth Distributionscited by 37
  4. 2021Shadow Generation for Composite Image in Real-world Scenescited by 35
  5. 2022Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertioncited by 35
  6. 2023EverLight: Indoor-Outdoor Editable HDR Lighting Estimationcited by 32
  7. 2022OutCast: Outdoor Single-image Relighting with Cast Shadowscited by 30
  8. 2023SpecNeRF: Gaussian Directional Encoding for Specular Reflectionscited by 30
  9. 2021GMLight: Lighting Estimation via Geometric Distribution Approximationcited by 28
  10. 2024Photorealistic Object Insertion with Diffusion-Guided Inverse Renderingcited by 27
  11. 2022Multi-view Inverse Rendering for Large-scale Real-world Indoor Scenescited by 23
  12. 2025A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Visioncited by 23
  13. 2023LightSim: Neural Lighting Simulation for Urban Scenescited by 20
  14. 2024IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Imagescited by 19
  15. 2021Sparse Needlets for Lighting Estimation with Spherical Transport Losscited by 18
  16. 2024Shadow Generation for Composite Image Using Diffusion modelcited by 17
  17. 2024Latent Intrinsics Emerge from Training to Relightcited by 17
  18. 2024ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusioncited by 16
  19. 20233D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detectioncited by 15
  20. 2023Beyond the Pixel: a Photometrically Calibrated HDR Dataset for Luminance and Color Predictioncited by 14
  21. 2025LuxDiT: Lighting Estimation with Video Diffusion Transformercited by 14
  22. 2023Accidental Light Probescited by 13
  23. 2022Editable Indoor Lighting Estimationcited by 12
  24. 2023MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimationcited by 12
  25. 2023Spatiotemporally Consistent HDR Indoor Lighting Estimationcited by 12
  26. 2021Lighting, Reflectance and Geometry Estimation from 360circ Panoramic Stereocited by 11
  27. 2021Deep Image-based Illumination Harmonizationcited by 11
  28. 2023Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectancecited by 11
  29. 2025GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDRcited by 11
  30. 2025DiffusionLight-Turbo: Accelerated Light Probes for Free via Single-Pass Chrome Ball Inpaintingcited by 11
  31. 2025DNF-Intrinsic: Deterministic Noise-Free Diffusion for Indoor Inverse Renderingcited by 11
  32. 2024OPa-Ma: Text Guided Mamba for 360-degree Image Out-paintingcited by 7
  33. 2022Deep Graph Learning for Spatially-Varying Indoor Lighting Predictioncited by 6
  34. 2023Foreground Object Search by Distilling Composite Image Featurecited by 6
  35. 2024Relighting from a Single Image: Datasets and Deep Intrinsic-based Architecturecited by 6
  36. 2025MatSwap: Light-aware material transfers in imagescited by 6
  37. 2023Zero Grads: Learning Local Surrogate Losses for Non-Differentiable Graphicscited by 5
  38. 2023A Real-time Method for Inserting Virtual Objects into Neural Radiance Fieldscited by 5

50 most cited of 82 All 82 (JSON)