mlsanityData to 7 Oct 2026

A Dataset of Multi-Illumination Images in the Wild

arXiv 1910.08131 ↗First posted 17 Oct 2019cs.CVcited by 45

Not on the map. Why?

Abstract (arXiv)

Collections of images under a single, uncontrolled illumination have enabled the rapid advancement of core computer vision tasks like classification, detection, and segmentation. But even with modern learning techniques, many inverse problems involving lighting and material understanding remain too severely ill-posed to be solved with single-illumination datasets. To fill this gap, we introduce a new multi-illumination dataset of more than 1000 real scenes, each captured under 25 lighting conditions. We demonstrate the richness of this dataset by training state-of-the-art models for three challenging applications: single-image illumination estimation, image relighting, and mixed-illuminant white balance.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 4; 2023: 5; 2024: 7; 2025: 7; 2026: 13.

45 papers.

Sort:

By area:

  1. 2021Making Images Real Again: A Comprehensive Survey on Deep Image Compositioncited by 63
  2. 2021Free-viewpoint Indoor Neural Relighting from Multi-view Stereocited by 50
  3. 2025LightLab: Controlling Light Sources in Images with Diffusion Modelscited by 36
  4. 2023OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objectscited by 31
  5. 2021GMLight: Lighting Estimation via Geometric Distribution Approximationcited by 28
  6. 2023Materialistic: Selecting Similar Materials in Imagescited by 26
  7. 2021Auto White-Balance Correction for Mixed-Illuminant Scenescited by 22
  8. 2022A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsingcited by 22
  9. 2021Sparse Needlets for Lighting Estimation with Spherical Transport Losscited by 18
  10. 2024Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relightingcited by 18
  11. 2021Plan2Scene: Converting Floorplans to 3D Scenescited by 17
  12. 2024Latent Intrinsics Emerge from Training to Relightcited by 17
33 more
  1. 2025IntrinsicEdit: Precise generative image manipulation in intrinsic spacecited by 17
  2. 2024SAMa: Material-aware 3D Selection and Segmentationcited by 9
  3. 2024Attentive Illumination Decomposition Model for Multi-Illuminant White Balancingcited by 8
  4. 2023Lasagna: Layered Score Distillation for Disentangled Object Relightingcited by 7
  5. 2024Relighting from a Single Image: Datasets and Deep Intrinsic-based Architecturecited by 6
  6. 2021DSRN: an Efficient Deep Network for Image Relightingcited by 5
  7. 2023Towards High-Quality Specular Highlight Removal by Leveraging Large-Scale Synthetic Datacited by 5
  8. 2023Computational Flash Photography through Intrinsicscited by 4
  9. 2025After the Party: Navigating the Mapping From Color to Ambient Lightingcited by 4
  10. 2026LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction under Multi-illumination Conditionscited by 4
  11. 2022Designing An Illumination-Aware Network for Deep Image Relightingcited by 3
  12. 2025Fine-Grained Spatially Varying Material Selection in Imagescited by 3
  13. 2021Deep Portrait Lighting Enhancement with 3D Guidancecited by 2
  14. 2024MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fieldscited by 1
  15. 2025UAVLight: A Benchmark for Illumination-Robust 3D Reconstruction in Unmanned Aerial Vehicle (UAV) Scenescited by 1
  16. 2026ICTPolarReal: A Polarized Reflection and Material Dataset of Real World Objectscited by 1
  17. 2026Shedding Light: A Benchmark for Evaluating Lighting Understanding in Generative Image Modelscited by 1
  18. 2021Predicting Surface Reflectance Properties of Outdoor Scenes Under Unknown Natural Illuminationcited by 0
  19. 2022M2-Net: Multi-stages Specular Highlight Detection and Removal in Multi-scenescited by 0
  20. 2022A novel illumination condition varied image dataset-Food Vision Dataset (FVD) for fair and reliable consumer acceptability predictions from foodcited by 0
  21. 2024Learning Relighting and Intrinsic Decomposition in Neural Radiance Fieldscited by 0
  22. 2025Improving the color accuracy of lighting estimation modelscited by 0
  23. 2025Robust Non-negative Proximal Gradient Algorithm for Inverse Problemscited by 0
  24. 2026SyncLight: Single-Edit Multi-View Relightingcited by 0
  25. 2026Adaptive Illumination Control for Robot Perceptioncited by 0
  26. 2026FMMC: Harnessing the Power of Foundation Models for Accurate Material Classificationcited by 0
  27. 2026LightMover: Generative Light Movement with Color and Intensity Controlscited by 0
  28. 2026WildRelight: A Real-World Benchmark and Physics-Guided Adaptation for Single-Image Relightingcited by 0
  29. 2026PIXLRelight: Controllable Relighting via Intrinsic Conditioningcited by 0
  30. 2026Video Generation Models Are Inherent Lighting Estimatorscited by 0
  31. 2026LightCrafter: PBR-Conditioned Video Diffusion Refinement for Controllable and Consistent Relightingcited by 0
  32. 2026Consistent Feature Transport for Image Relightingcited by 0
  33. 2026Dior: Drawing the Light of Image via Material-Decoupled Illumination Representationcited by 0