# Unsupervised Learning for Intrinsic Image Decomposition from a Single Image

arXiv: https://arxiv.org/abs/1911.09930 · HTML: https://mlsanity.com/paper/1911.09930/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Nov 2019.

## Built on by (most cited first, 30 of 55)

- [IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illumination](https://mlsanity.com/paper/2404.11593/) (2024)
- [Intrinsic Image Decomposition via Ordinal Shading](https://mlsanity.com/paper/2311.12792/) (2023)
- [DIB-R++: Learning to Predict Lighting and Material with a Hybrid Differentiable Renderer](https://mlsanity.com/paper/2111.00140/) (2021)
- [IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis](https://mlsanity.com/paper/2210.00647/) (2022)
- [StyleGAN knows Normal, Depth, Albedo, and More](https://mlsanity.com/paper/2306.00987/) (2023)
- [Colorful Diffuse Intrinsic Image Decomposition in the Wild](https://mlsanity.com/paper/2409.13690/) (2024)
- [Relighting4D: Neural Relightable Human from Videos](https://mlsanity.com/paper/2207.07104/) (2022)
- [A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyond](https://mlsanity.com/paper/2112.03842/) (2021)
- [De-rendering 3D Objects in the Wild](https://mlsanity.com/paper/2201.02279/) (2022)
- [Material Palette: Extraction of Materials from a Single Image](https://mlsanity.com/paper/2311.17060/) (2023)
- [PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image Decomposition](https://mlsanity.com/paper/2203.16670/) (2022)
- [Generating Visual Scenes from Touch](https://mlsanity.com/paper/2309.15117/) (2023)
- [Neural LightRig: Unlocking Accurate Object Normal and Material Estimation with Multi-Light Diffusion](https://mlsanity.com/paper/2412.09593/) (2024)
- [Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning](https://mlsanity.com/paper/2211.14751/) (2022)
- [Measured Albedo in the Wild: Filling the Gap in Intrinsics Evaluation](https://mlsanity.com/paper/2306.15662/) (2023)
- [Weakly-supervised Single-view Image Relighting](https://mlsanity.com/paper/2303.13852/) (2023)
- [Seeing a Rose in Five Thousand Ways](https://mlsanity.com/paper/2212.04965/) (2022)
- [ReliTalk: Relightable Talking Portrait Generation from a Single Video](https://mlsanity.com/paper/2309.02434/) (2023)
- [Generative Portrait Shadow Removal](https://mlsanity.com/paper/2410.05525/) (2024)
- [Physics-informed Guided Disentanglement in Generative Networks](https://mlsanity.com/paper/2107.14229/) (2021)
- [SuperMat: Physically Consistent PBR Material Estimation at Interactive Rates](https://mlsanity.com/paper/2411.17515/) (2024)
- [PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling](https://mlsanity.com/paper/2504.14219/) (2025)
- [Complementary Feature Enhanced Network with Vision Transformer for Image Dehazing](https://mlsanity.com/paper/2109.07100/) (2021)
- [CRFormer: A Cross-Region Transformer for Shadow Removal](https://mlsanity.com/paper/2207.01600/) (2022)
- [Few-shot Neural Radiance Fields Under Unconstrained Illumination](https://mlsanity.com/paper/2303.11728/) (2023)
- [Unsupervised Intrinsic Image Decomposition with LiDAR Intensity](https://mlsanity.com/paper/2303.10820/) (2023)
- [Relighting from a Single Image: Datasets and Deep Intrinsic-based Architecture](https://mlsanity.com/paper/2409.18770/) (2024)
- [Relighting Scenes with Object Insertions in Neural Radiance Fields](https://mlsanity.com/paper/2406.14806/) (2024)
- [SILT: Self-supervised Lighting Transfer Using Implicit Image Decomposition](https://mlsanity.com/paper/2110.12914/) (2021)
- [JoIN: Joint GANs Inversion for Intrinsic Image Decomposition](https://mlsanity.com/paper/2305.11321/) (2023)

## Abstract (arXiv)

Intrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene. It is challenging since it needs to separate one image into two components. To tackle this, conventional methods introduce various priors to constrain the solution, yet with limited performance. Meanwhile, the problem is typically solved by supervised learning methods, which is actually not an ideal solution since obtaining ground truth reflectance and shading for massive general natural scenes is challenging and even impossible. In this paper, we propose a novel unsupervised intrinsic image decomposition framework, which relies on neither labeled training data nor hand-crafted priors. Instead, it directly learns the latent feature of reflectance and shading from unsupervised and uncorrelated data. To enable this, we explore the independence between reflectance and shading, the domain invariant content constraint and the physical constraint. Extensive experiments on both synthetic and real image datasets demonstrate consistently superior performance of the proposed method.