--- title: Intrinsic emoji: 🐢 colorFrom: blue colorTo: red sdk: gradio sdk_version: 5.0.1 app_file: app.py pinned: false license: cc-by-nc-sa-4.0 --- # Intrinsic Image Decomposition This space contains a demo for the following papers: **Colorful Diffuse Intrinsic Image Decomposition in the Wild**, [Chris Careaga](https://ccareaga.github.io/) and [Yağız Aksoy](https://yaksoy.github.io), ACM Transactions on Graphics, 2024 \ [Project](https://yaksoy.github.io/ColorfulShading/) | [Paper](https://yaksoy.github.io/papers/TOG24-ColorfulShading.pdf) | [Supplementary](https://yaksoy.github.io/papers/TOG24-ColorfulShading-supp.pdf) | [HF](https://huggingface.co/papers/2409.13690) **Intrinsic Image Decomposition via Ordinal Shading**, [Chris Careaga](https://ccareaga.github.io/) and [Yağız Aksoy](https://yaksoy.github.io), ACM Transactions on Graphics, 2023 \ [Project](https://yaksoy.github.io/intrinsic/) | [Paper](https://yaksoy.github.io/papers/TOG23-Intrinsic.pdf) | [Video](https://www.youtube.com/watch?v=pWtJd3hqL3c) | [Supplementary](https://yaksoy.github.io/papers/TOG23-Intrinsic-Supp.pdf) | [Data](https://github.com/compphoto/MIDIntrinsics) | [HF](https://huggingface.co/papers/2311.12792) We propose a method for generating high-resolution intrinsic image decompositions for in-the-wild images. Our method consists of multiple stages. We first estimate a grayscale shading layer using our ordinal shading pipeline. We then estimate low-resolution chromaticity information to account for colorful illumination effects while maintaining global consistency. Using this initial colorful decomposition, we estimate a high-resolution, sparse albedo layer. We show that our decomposition allows us to train a diffuse shading estimation network using only a single rendered indoor dataset. ![representative](https://github.com/compphoto/Intrinsic/blob/main/figures/representative.png?raw=true) Our estimated components unlock multiple illumination-aware editing operations such as per-pixel white balancing and specularity removal: ![applications](https://github.com/compphoto/Intrinsic/blob/main/figures/app_teaser2.jpg?raw=true)