mlsanityData to 7 Oct 2026

Accidental Light Probes

arXiv 2301.05211 ↗First posted 12 Jan 2023cs.CV cs.GRcited by 13

Not on the map. Why?

Abstract (arXiv)

Recovering lighting in a scene from a single image is a fundamental problem in computer vision. While a mirror ball light probe can capture omnidirectional lighting, light probes are generally unavailable in everyday images. In this work, we study recovering lighting from accidental light probes (ALPs) -- common, shiny objects like Coke cans, which often accidentally appear in daily scenes. We propose a physically-based approach to model ALPs and estimate lighting from their appearances in single images. The main idea is to model the appearance of ALPs by photogrammetrically principled shading and to invert this process via differentiable rendering to recover incidental illumination. We demonstrate that we can put an ALP into a scene to allow high-fidelity lighting estimation. Our model can also recover lighting for existing images that happen to contain an ALP.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 32 of its 62 references that are in the map. First posted on arXiv 12 Jan 2023.

Builds on

32 of 62 references.

References · 32

  1. 2020End-to-End Object Detection with Transformerscited by 7,384
  2. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  3. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  4. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  5. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 439
  6. 2020U2-Net: Going Deeper with Nested U-Structure for Salient Object Detectioncited by 410
  7. 2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 363
  8. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  9. 2019Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Imagecited by 202
  10. 2022Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoisingcited by 163
  11. 2017Learning to Predict Indoor Illumination from a Single Imagecited by 160
  12. 2019Single Image Portrait Relightingcited by 152
20 more
  1. 2022IRON: Inverse Rendering by Optimizing Neural SDFs and Materials from Photometric Imagescited by 110
  2. 2019Neural Inverse Rendering of an Indoor Scene from a Single Imagecited by 101
  3. 2020Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Renderingcited by 101
  4. 2018InverseRenderNet: Learning single image inverse renderingcited by 100
  5. 2019Deep Parametric Indoor Lighting Estimationcited by 82
  6. 2021Learning Indoor Inverse Rendering with 3D Spatially-Varying Lightingcited by 82
  7. 2019Fast Spatially-Varying Indoor Lighting Estimationcited by 72
  8. 2019DeepLight: Learning Illumination for Unconstrained Mobile Mixed Realitycited by 63
  9. 2020Lighthouse: Predicting Lighting Volumes for Spatially-Coherent Illuminationcited by 62
  10. 2022StyleLight: HDR Panorama Generation for Lighting Estimation and Editingcited by 59
  11. 2019Neural Illumination: Lighting Prediction for Indoor Environmentscited by 57
  12. 2020EMLight: Lighting Estimation via Spherical Distribution Approximationcited by 47
  13. 2019Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR Applicationscited by 39
  14. 2022Neural Light Field Estimation for Street Scenes with Differentiable Virtual Object Insertioncited by 35
  15. 2020Seeing the World in a Bag of Chipscited by 25
  16. 2020Object-based Illumination Estimation with Rendering-aware Neural Networkscited by 19
  17. 2021Sparse Needlets for Lighting Estimation with Spherical Transport Losscited by 18
  18. 2018Learning to Estimate Indoor Lighting from 3D Objectscited by 17
  19. 2020Learning Illumination from Diverse Portraitscited by 15
  20. 2018Faces as Lighting Probes via Unsupervised Deep Highlight Extractioncited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 5; 2025: 3; 2026: 1.

13 papers.

Sort:

By area:

  1. 2023DiffusionLight: Light Probes for Free by Painting a Chrome Ballcited by 63
  2. 2023Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmarkcited by 51
  3. 2024Photorealistic Object Insertion with Diffusion-Guided Inverse Renderingcited by 27
  4. 2023LightSim: Neural Lighting Simulation for Urban Scenescited by 20
  5. 2025LuxDiT: Lighting Estimation with Video Diffusion Transformercited by 14
  6. 2024Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variationcited by 13
  7. 2023Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectancecited by 11
  8. 2025DiffusionLight-Turbo: Accelerated Light Probes for Free via Single-Pass Chrome Ball Inpaintingcited by 11
  9. 2025Materialist: Physically Based Editing Using Single-Image Inverse Renderingcited by 10
  10. 2024Relighting Scenes with Object Insertions in Neural Radiance Fieldscited by 5
  11. 2024MAIR++: Improving Multi-view Attention Inverse Rendering with Implicit Lighting Representationcited by 3
  12. 2024MixLight: Borrowing the Best of both Spherical Harmonics and Gaussian Modelscited by 1
1 more
  1. 2026Under One Sun: Multi-Object Generative Perception of Materials and Illuminationcited by 0