mlsanityData to 14 Oct 2026

Deep Sky Modeling for Single Image Outdoor Lighting Estimation

arXiv 1905.03897 ↗First posted 10 May 2019cs.CVcited by 66

Not on the map. Why?

Abstract (arXiv)

We propose a data-driven learned sky model, which we use for outdoor lighting estimation from a single image. As no large-scale dataset of images and their corresponding ground truth illumination is readily available, we use complementary datasets to train our approach, combining the vast diversity of illumination conditions of SUN360 with the radiometrically calibrated and physically accurate Laval HDR sky database. Our key contribution is to provide a holistic view of both lighting modeling and estimation, solving both problems end-to-end. From a test image, our method can directly estimate an HDR environment map of the lighting without relying on analytical lighting models. We demonstrate the versatility and expressivity of our learned sky model and show that it can be used to recover plausible illumination, leading to visually pleasant virtual object insertions. To further evaluate our method, we capture a dataset of HDR 360deg panoramas and show through extensive validation that we significantly outperform previous state-of-the-art.

Key facts. Cited by 66 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 14; 2022: 8; 2023: 8; 2024: 16; 2025: 16; 2026: 4.

66 papers.

Sort:

By area:

  1. 2024Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agentscited by 91
  2. 2023Neural Fields meet Explicit Geometric Representation for Inverse Rendering of Urban Scenescited by 90
  3. 2021Learning Indoor Inverse Rendering with 3D Spatially-Varying Lightingcited by 83
  4. 2023DiffusionLight: Light Probes for Free by Painting a Chrome Ballcited by 64
  5. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  6. 2024LightIt: Illumination Modeling and Control for Diffusion Modelscited by 57
  7. 2021DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderercited by 52
  8. 2021Neural Video Portrait Relighting in Real-time via Consistency Modelingcited by 46
  9. 2021Deep Learning for HDR Imaging: State-of-the-Art and Future Trendscited by 45
  10. 2022Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertioncited by 35
  11. 2023EverLight: Indoor-Outdoor Editable HDR Lighting Estimationcited by 32
  12. 2021Single-image Full-body Human Relightingcited by 30
38 more
  1. 2022OutCast: Outdoor Single-image Relighting with Cast Shadowscited by 30
  2. 2024Photorealistic Object Insertion with Diffusion-Guided Inverse Renderingcited by 27
  3. 2024Lite2Relight: 3D-aware Single Image Portrait Relightingcited by 25
  4. 2025A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Visioncited by 24
  5. 20253D Scene Generation: A Surveycited by 24
  6. 2024RelitLRM: Generative Relightable Radiance for Large Reconstruction Modelscited by 23
  7. 2023LightSim: Neural Lighting Simulation for Urban Scenescited by 20
  8. 2024IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Imagescited by 20
  9. 2021Luminance Attentive Networks for HDR Image and Panorama Reconstructioncited by 18
  10. 2022Factorized and Controllable Neural Re-Rendering of Outdoor Scene for Photo Extrapolationcited by 16
  11. 2025LuxDiT: Lighting Estimation with Video Diffusion Transformercited by 15
  12. 2021Spatially-Varying Outdoor Lighting Estimation from Intrinsicscited by 14
  13. 2024Authentic Hand Avatar from a Phone Scan via Universal Hand Modelcited by 13
  14. 2025GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDRcited by 12
  15. 2025DiffusionLight-Turbo: Accelerated Light Probes for Free via Single-Pass Chrome Ball Inpaintingcited by 12
  16. 2025AirSim360: A Panoramic Simulation Platform within Drone Viewcited by 12
  17. 2021Efficient and Differentiable Shadow Computation for Inverse Problemscited by 11
  18. 2024Generative Portrait Shadow Removalcited by 10
  19. 2025Seeing through Satellite Images at Street Viewscited by 9
  20. 2025Restereo: Diffusion stereo video generation and restorationcited by 7
  21. 2021Repopulating Street Scenescited by 6
  22. 2021DeRenderNet: Intrinsic Image Decomposition of Urban Scenes with Shape-(In)dependent Shading Renderingcited by 6
  23. 2022Deep Graph Learning for Spatially-Varying Indoor Lighting Predictioncited by 6
  24. 2023RENI++ A Rotation-Equivariant, Scale-Invariant, Natural Illumination Priorcited by 6
  25. 2024COMPOSE: Comprehensive Portrait Shadow Editingcited by 6
  26. 2025Spatiotemporally Consistent Indoor Lighting Estimation with Diffusion Priorscited by 6
  27. 2024EdgeRelight360: Text-Conditioned 360-Degree HDR Image Generation for Real-Time On-Device Video Portrait Relightingcited by 5
  28. 2023Scene-Conditional 3D Object Stylization and Compositioncited by 4
  29. 2025UniLight: A Unified Representation for Lightingcited by 4
  30. 2021PhotoApp: Photorealistic Appearance Editing of Head Portraitscited by 3
  31. 2022Time-of-Day Neural Style Transfer for Architectural Photographscited by 3
  32. 2023Animating Street Viewcited by 3
  33. 2024360U-Former: HDR Illumination Estimation with Panoramic Adapted Vision Transformerscited by 3
  34. 2025BOOTPLACE: Bootstrapped Object Placement with Detection Transformerscited by 3
  35. 2025Minimal Sensing for Orienting a Solar Panelcited by 3
  36. 2021Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramascited by 2
  37. 2022Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences using Transformer Networkscited by 2
  38. 2022Improving generalization by mimicking the human visual dietcited by 2

50 most cited of 66 All 66 (JSON)