{"url":"/task/intrinsic-image-decomposition","name":"Intrinsic Image Decomposition","slug":"intrinsic-image-decomposition","description_markdown":"**Intrinsic Image Decomposition** is the process of separating an image into its formation components such as reflectance (albedo) and shading (illumination). Reflectance is the color of the object, invariant to camera viewpoint and illumination conditions, whereas shading, dependent on camera viewpoint and object geometry, consists of different illumination effects, such as shadows, shading and inter-reflections. Using intrinsic images, instead of the original images, can be beneficial for many computer vision algorithms. For instance, for shape-from-shading algorithms, the shading images contain important visual cues to recover geometry, while for segmentation and detection algorithms, reflectance images can be beneficial as they are independent of confounding illumination effects. Furthermore, intrinsic images are used in a wide range of computational photography applications, such as material recoloring, relighting, retexturing and stylization.\n\n\n<span class=\"description-source\">Source: [CNN based Learning using Reflection and Retinex Models for Intrinsic Image Decomposition ](https://arxiv.org/abs/1712.01056)</span>","categories":[{"name":"Computer Vision","url":"/area/computer-vision"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":85,"papers_with_code":28,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":8,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/mpi-sintel","name":"MPI Sintel","full_name":"","num_papers_in_archive":198},{"url":"/dataset/hypersim","name":"Hypersim","full_name":"","num_papers_in_archive":108},{"url":"/dataset/futurehouse","name":"FutureHouse","full_name":"","num_papers_in_archive":3},{"url":"/dataset/ibl-nerf","name":"IBL-NeRF","full_name":"","num_papers_in_archive":2},{"url":"/dataset/shapenet-intrinsic-images-v1-0","name":"ShapeNet Intrinsic Images v1.0","full_name":"","num_papers_in_archive":2},{"url":"/dataset/doc3dshade","name":"Doc3DShade","full_name":"","num_papers_in_archive":1},{"url":"/dataset/mid-intrinsics","name":"MID Intrinsics","full_name":"","num_papers_in_archive":1},{"url":"/dataset/shapenet-intrinsic-images-v2-0-extended","name":"ShapeNet Intrinsic Images v2.0 Extended","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":28,"of":28,"tagged_in_all":85,"items":[{"url":"/paper/exploiting-diffusion-prior-for-generalizable","title":"Exploiting Diffusion Prior for Generalizable Dense Prediction","date":"2023-11-30","arxiv_id":"2311.18832","repositories_listed":2,"syntology":{"n":5,"n_ran":4,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/intrinsic-image-decomposition-via-ordinal-1","title":"Intrinsic Image Decomposition via Ordinal Shading","date":"2023-11-21","arxiv_id":"2311.12792","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/illumination-aware-image-quality-assessment","title":"Illumination-Aware Image Quality Assessment for Enhanced Low-light Image","date":"2021-10-22","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-learning-for-intrinsic-image","title":"Unsupervised Learning for Intrinsic Image Decomposition from a Single Image","date":"2019-11-22","arxiv_id":"1911.09930","repositories_listed":2,"syntology":null},{"url":"/paper/endomust-monocular-depth-estimation-for","title":"EndoMUST: Monocular Depth Estimation for Robotic Endoscopy via End-to-end Multi-step Self-supervised Training","date":"2025-06-19","arxiv_id":"2506.16017","repositories_listed":1,"syntology":null},{"url":"/paper/ps-diffusion-photorealistic-subject-driven","title":"PS-Diffusion: Photorealistic Subject-Driven Image Editing with Disentangled Control and Attention","date":"2025-01-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/mli-nerf-multi-light-intrinsic-aware-neural","title":"MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fields","date":"2024-11-26","arxiv_id":"2411.17235","repositories_listed":1,"syntology":null},{"url":"/paper/colorful-diffuse-intrinsic-image-1","title":"Colorful Diffuse Intrinsic Image Decomposition in the Wild","date":"2024-09-20","arxiv_id":"2409.13690","repositories_listed":1,"syntology":null},{"url":"/paper/a-general-albedo-recovery-approach-for-aerial","title":"A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse Rendering","date":"2024-09-04","arxiv_id":"2409.03032","repositories_listed":1,"syntology":null},{"url":"/paper/hyperdid-hyperspectral-intrinsic-image","title":"HyperDID: Hyperspectral Intrinsic Image Decomposition with Deep Feature Embedding","date":"2023-11-25","arxiv_id":"2311.14899","repositories_listed":1,"syntology":null},{"url":"/paper/intrinsic-appearance-decomposition-using","title":"Intrinsic Image Decomposition Using Point Cloud Representation","date":"2023-07-20","arxiv_id":"2307.10924","repositories_listed":1,"syntology":null},{"url":"/paper/dpf-learning-dense-prediction-fields-with","title":"DPF: Learning Dense Prediction Fields with Weak Supervision","date":"2023-03-29","arxiv_id":"2303.16890","repositories_listed":1,"syntology":{"n":34,"n_ran":23,"n_unverified":11,"n_pointer_only":34}},{"url":"/paper/unsupervised-intrinsic-image-decomposition","title":"Unsupervised Intrinsic Image Decomposition with LiDAR Intensity","date":"2023-03-20","arxiv_id":"2303.10820","repositories_listed":1,"syntology":null},{"url":"/paper/seeing-a-rose-in-five-thousand-ways","title":"Seeing a Rose in Five Thousand Ways","date":"2022-12-09","arxiv_id":"2212.04965","repositories_listed":1,"syntology":null},{"url":"/paper/estimating-reflectance-layer-from-a-single","title":"Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning","date":"2022-11-27","arxiv_id":"2211.14751","repositories_listed":1,"syntology":null},{"url":"/paper/signet-intrinsic-image-decomposition-by-a","title":"SIGNet: Intrinsic Image Decomposition by a Semantic and Invariant Gradient Driven Network for Indoor Scenes","date":"2022-08-30","arxiv_id":"2208.14369","repositories_listed":1,"syntology":null},{"url":"/paper/shoerinsics-shoeprint-prediction-for","title":"Creating a Forensic Database of Shoeprints from Online Shoe Tread Photos","date":"2022-05-04","arxiv_id":"2205.02361","repositories_listed":1,"syntology":null},{"url":"/paper/pie-net-photometric-invariant-edge-guided","title":"PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image Decomposition","date":"2022-03-30","arxiv_id":"2203.16670","repositories_listed":1,"syntology":null},{"url":"/paper/hybrid-local-global-transformer-for-image","title":"Complementary Feature Enhanced Network with Vision Transformer for Image Dehazing","date":"2021-09-15","arxiv_id":"2109.07100","repositories_listed":1,"syntology":null},{"url":"/paper/intrinsic-image-transfer-for-illumination","title":"Intrinsic Image Transfer for Illumination Manipulation","date":"2021-07-01","arxiv_id":"2107.00704","repositories_listed":1,"syntology":null},{"url":"/paper/physically-inspired-dense-fusion-networks-for","title":"Physically Inspired Dense Fusion Networks for Relighting","date":"2021-05-05","arxiv_id":"2105.02209","repositories_listed":1,"syntology":null},{"url":"/paper/outdoor-inverse-rendering-from-a-single-image","title":"Outdoor inverse rendering from a single image using multiview self-supervision","date":"2021-02-12","arxiv_id":"2102.06591","repositories_listed":1,"syntology":null},{"url":"/paper/intrinsic-decomposition-of-document-images-in","title":"Intrinsic Decomposition of Document Images In-the-Wild","date":"2020-11-29","arxiv_id":"2011.14447","repositories_listed":1,"syntology":null},{"url":"/paper/shadingnet-image-intrinsics-by-fine-grained","title":"ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition","date":"2019-12-09","arxiv_id":"1912.04023","repositories_listed":1,"syntology":null},{"url":"/paper/learning-blind-video-temporal-consistency","title":"Learning Blind Video Temporal Consistency","date":"2018-08-01","arxiv_id":"1808.00449","repositories_listed":1,"syntology":null},{"url":"/paper/joint-learning-of-intrinsic-images-and","title":"Joint Learning of Intrinsic Images and Semantic Segmentation","date":"2018-07-31","arxiv_id":"1807.11857","repositories_listed":1,"syntology":null},{"url":"/paper/learning-intrinsic-image-decomposition-from","title":"Learning Intrinsic Image Decomposition from Watching the World","date":"2018-04-02","arxiv_id":"1804.00582","repositories_listed":1,"syntology":null},{"url":"/paper/unified-depth-prediction-and-intrinsic-image","title":"Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fields","date":"2016-03-21","arxiv_id":"1603.06359","repositories_listed":1,"syntology":null}],"syntology_records":3,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}