mlsanityData to 7 Oct 2026

All-Weather Deep Outdoor Lighting Estimation

arXiv 1906.04909 ↗First posted 12 Jun 2019cs.CVcited by 41

Not on the map. Why?

Abstract (arXiv)

We present a neural network that predicts HDR outdoor illumination from a single LDR image. At the heart of our work is a method to accurately learn HDR lighting from LDR panoramas under any weather condition. We achieve this by training another CNN (on a combination of synthetic and real images) to take as input an LDR panorama, and regress the parameters of the Lalonde-Matthews outdoor illumination model. This model is trained such that it a) reconstructs the appearance of the sky, and b) renders the appearance of objects lit by this illumination. We use this network to label a large-scale dataset of LDR panoramas with lighting parameters and use them to train our single image outdoor lighting estimation network. We demonstrate, via extensive experiments, that both our panorama and single image networks outperform the state of the art, and unlike prior work, are able to handle weather conditions ranging from fully sunny to overcast skies.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 10; 2023: 8; 2024: 5; 2025: 8; 2026: 3.

41 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 89
  3. 2021Learning Indoor Inverse Rendering with 3D Spatially-Varying Lightingcited by 82
  4. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  5. 2021Deep Learning for HDR Imaging: State-of-the-Art and Future Trendscited by 45
  6. 2021Shadow Generation for Composite Image in Real-world Scenescited by 35
  7. 2022Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertioncited by 35
  8. 2023EverLight: Indoor-Outdoor Editable HDR Lighting Estimationcited by 32
  9. 2022OutCast: Outdoor Single-image Relighting with Cast Shadowscited by 30
  10. 2025A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Visioncited by 23
  11. 2023UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Videocited by 22
  12. 2023LightSim: Neural Lighting Simulation for Urban Scenescited by 20
29 more
  1. 2024IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Imagescited by 19
  2. 2021Sparse Needlets for Lighting Estimation with Spherical Transport Losscited by 18
  3. 2024Shadow Generation for Composite Image Using Diffusion modelcited by 17
  4. 2021Spatially-Varying Outdoor Lighting Estimation from Intrinsicscited by 14
  5. 2023Intrinsic Harmonization for Illumination-Aware Compositingcited by 11
  6. 2022nLMVS-Net: Deep Non-Lambertian Multi-View Stereocited by 10
  7. 2022GeoFill: Reference-Based Image Inpainting with Better Geometric Understandingcited by 9
  8. 2025Seeing through Satellite Images at Street Viewscited by 8
  9. 2022Deep Graph Learning for Spatially-Varying Indoor Lighting Predictioncited by 6
  10. 2023Foreground Object Search by Distilling Composite Image Featurecited by 6
  11. 2023Towards a Perceptual Evaluation Framework for Lighting Estimationcited by 5
  12. 2023Scene-Conditional 3D Object Stylization and Compositioncited by 4
  13. 2024360U-Former: HDR Illumination Estimation with Panoramic Adapted Vision Transformerscited by 3
  14. 2025UniLight: A Unified Representation for Lightingcited by 3
  15. 2022Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences using Transformer Networkscited by 2
  16. 2021Spatially and color consistent environment lighting estimation using deep neural networks for mixed realitycited by 1
  17. 2022Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplaciancited by 1
  18. 2022Shadow Removal by High-Quality Shadow Synthesiscited by 1
  19. 2025Lighting in Motion: Spatiotemporal HDR Lighting Estimationcited by 1
  20. 2026Shedding Light: A Benchmark for Evaluating Lighting Understanding in Generative Image Modelscited by 1
  21. 2022RiCS: A 2D Self-Occlusion Map for Harmonizing Volumetric Objectscited by 0
  22. 2022Framework for 2D Ad placements in LinearTVcited by 0
  23. 2024Augmented Reality based Simulated Data (ARSim) with multi-view consistency for AV perception networkscited by 0
  24. 2025HDR Environment Map Estimation with Latent Diffusion Modelscited by 0
  25. 2025Embedding Physical Reasoning into Diffusion-Based Shadow Generation Under the Sun and Skycited by 0
  26. 2025Cast and Attached Shadow Detection via Iterative Light and Geometry Reasoningcited by 0
  27. 2025Towards Physically-Based Sky-Modeling For Image Based Lightingcited by 0
  28. 2026VSDiffusion: Taming Ill-Posed Shadow Generation via Visibility-Constrained Diffusioncited by 0
  29. 2026Bridging the Generalization Gap in Adverse Weather Segmentation: A Training Recipe Perspectivecited by 0