mlsanityData to 14 Oct 2026

A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyond

arXiv 2112.03842 ↗First posted 7 Dec 2021cs.CVcited by 37

Not on the map. Why?

Abstract (arXiv)

Intrinsic imaging or intrinsic image decomposition has traditionally been described as the problem of decomposing an image into two layers: a reflectance, the albedo invariant color of the material; and a shading, produced by the interaction between light and geometry. Deep learning techniques have been broadly applied in recent years to increase the accuracy of those separations. In this survey, we overview those results in context of well-known intrinsic image data sets and relevant metrics used in the literature, discussing their suitability to predict a desirable intrinsic image decomposition. Although the Lambertian assumption is still a foundational basis for many methods, we show that there is increasing awareness on the potential of more sophisticated physically-principled components of the image formation process, that is, optically accurate material models and geometry, and more complete inverse light transport estimations. We classify these methods in terms of the type of decomposition, considering the priors and models used, as well as the learning architecture and methodology driving the decomposition process. We also provide insights about future directions for research, given the recent advances in neural, inverse and differentiable rendering techniques.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). Builds on 63 of its 154 references that are in the map. First posted on arXiv 7 Dec 2021.

Builds on

63 of 154 references.

References · 63

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  7. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  8. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  9. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  10. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,588
  11. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  12. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
38 more
  1. 2017Non-local Neural Networkscited by 2,293
  2. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 2,010
  3. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,591
  4. 2020NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collectionscited by 1,232
  5. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 915
  6. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  7. 2017Learning multiple visual domains with residual adapterscited by 557
  8. 2016Semantic Scene Completion from a Single Depth Imagecited by 472
  9. 2020ResNeSt: Split-Attention Networkscited by 445
  10. 2020State of the Art on Neural Renderingcited by 278
  11. 2019Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Imagecited by 203
  12. 2017Cost-Effective Active Learning for Deep Image Classificationcited by 166
  13. 2017MoFA: Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstructioncited by 163
  14. 2019Single Image Portrait Relightingcited by 152
  15. 2018Single-Image SVBRDF Capture with a Rendering-Aware Deep Networkcited by 116
  16. 2017SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wildcited by 110
  17. 2019Neural Inverse Rendering of an Indoor Scene from a Single Imagecited by 101
  18. 2020Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Renderingcited by 101
  19. 2016Controlling Perceptual Factors in Neural Style Transfercited by 100
  20. 2018InverseRenderNet: Learning single image inverse renderingcited by 100
  21. 2017Self-supervised Multi-level Face Model Learning for Monocular Reconstruction at over 250 Hzcited by 91
  22. 2019Learning Physics-guided Face Relighting under Directional Lightcited by 90
  23. 2015The Fast Bilateral Solvercited by 87
  24. 2019Image-based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Eracited by 87
  25. 2018CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Renderingcited by 85
  26. 2018Learn To Pay Attentioncited by 83
  27. 2018FML: Face Model Learning from Videoscited by 78
  28. 2018Learning Intrinsic Image Decomposition from Watching the Worldcited by 74
  29. 2017Neural Face Editing with Intrinsic Image Disentanglingcited by 70
  30. 2018Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Imagecited by 66
  31. 2019Inverse Path Tracing for Joint Material and Lighting Estimationcited by 62
  32. 2019Unsupervised Learning for Intrinsic Image Decomposition from a Single Imagecited by 55
  33. 2018Modeling Surface Appearance from a Single Photograph using Self-augmented Convolutional Neural Networkscited by 51
  34. 2018Active Learning for Deep Object Detectioncited by 50
  35. 2019Flexible SVBRDF Capture with a Multi-Image Deep Networkcited by 50
  36. 2017Self-Supervised Intrinsic Image Decompositioncited by 43
  37. 2016Learning Non-Lambertian Object Intrinsics across ShapeNet Categoriescited by 42
  38. 2015Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regressioncited by 33

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 4; 2023: 8; 2024: 12; 2025: 8; 2026: 5.

37 papers.

Sort:

By area:

  1. 2024RGBleftrightarrowX: Image decomposition and synthesis using material- and lighting-aware diffusion modelscited by 161
  2. 2023Intrinsic Image Decomposition via Ordinal Shadingcited by 53
  3. 2022IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesiscited by 50
  4. 2024Colorful Diffuse Intrinsic Image Decomposition in the Wildcited by 44
  5. 2024LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relightingcited by 38
  6. 2023Materialistic: Selecting Similar Materials in Imagescited by 26
  7. 2022Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learningcited by 18
  8. 2023Measured Albedo in the Wild: Filling the Gap in Intrinsics Evaluationcited by 16
  9. 2024ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusioncited by 16
  10. 2023UMat: Uncertainty-Aware Single Image High Resolution Material Capturecited by 11
  11. 2024Intrinsic Single-Image HDR Reconstructioncited by 11
  12. 2023Concept Distillation: Leveraging Human-Centered Explanations for Model Improvementcited by 10
25 more
  1. 2026LuxRemix: Lighting Decomposition and Remixing for Indoor Scenescited by 9
  2. 2024Specularity Factorization for Low-Light Enhancementcited by 6
  3. 2023JoIN: Joint GANs Inversion for Intrinsic Image Decompositioncited by 4
  4. 2024Synthetica: Large Scale Synthetic Data for Robot Perceptioncited by 3
  5. 2024Surf-NeRF: Surface Regularised Neural Radiance Fieldscited by 3
  6. 2026GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformerscited by 3
  7. 2023Tree-Structured Shading Decompositioncited by 2
  8. 2024A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse Renderingcited by 2
  9. 2025StableIntrinsic: Detail-preserving One-step Diffusion Model for Multi-view Material Estimationcited by 2
  10. 2024MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fieldscited by 1
  11. 2025Single-image Reflectance and Transmittance Estimation from Any Flatbed Scannercited by 1
  12. 2025SAIL: Self-supervised Albedo Estimation from Real Images with a Latent Diffusion Modelcited by 1
  13. 2025VT-Intrinsic: Physics-Based Decomposition of Reflectance and Shading using a Single Visible-Thermal Image Paircited by 1
  14. 2025Spectral Compressive Imaging via Chromaticity-Intensity Decompositioncited by 1
  15. 2025MVID: Feed-Forward Multi-View Intrinsic Image Decompositioncited by 1
  16. 2026LiWi: Layering in the Wildcited by 1
  17. 2022NeIF: Representing General Reflectance as Neural Intrinsics Fields for Uncalibrated Photometric Stereocited by 0
  18. 2022Deep scene-scale material estimation from multi-view indoor capturescited by 0
  19. 2023Intrinsic Image Decomposition Using Point Cloud Representationcited by 0
  20. 2024Development of Context-Sensitive Formulas to Obtain Constant Luminance Perception for a Foreground Object in Front of Backgrounds of Varying Luminancecited by 0
  21. 2024Learning Relighting and Intrinsic Decomposition in Neural Radiance Fieldscited by 0
  22. 2025Texture-aware Intrinsic Image Decomposition with Model- and Learning-based Priorscited by 0
  23. 2025Phieat: Physically Grounded Material Feature Representationcited by 0
  24. 2026Olbedo: An Albedo and Shading Aerial Dataset for Large-Scale Outdoor Environmentscited by 0
  25. 2026Intrinsic decomposition and editing of 3D Gaussian splatscited by 0