Browse State-of-the-Art › Intrinsic Image Decomposition
Intrinsic Image Decomposition
28 papers with code · 0 benchmarks · 8 datasets archive 2025-07-28
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.
Source: CNN based Learning using Reflection and Retinex Models for Intrinsic Image Decomposition
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
No benchmark for this task in the archive.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
8 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Papers archive 2025-07-28
archive papers tagged: 85 · with a code link: 28 · where Syntology ran a sample: 3 (2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (3 of 85 tagged: 2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 85 of 85, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
30 Nov 2023 2 repositories listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples) · 2 pointer-only (licence)Contents generated by recent advanced Text-to-Image (T2I) diffusion models are sometimes too imaginative for existing off-the-shelf dense predictors to estimate due to the immitigable domain gap.
-
21 Nov 2023 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)We encourage the model to learn an accurate decomposition by computing losses on the estimated shading as well as the albedo implied by the intrinsic model.
-
22 Oct 2021 2 repositories listedTo reduce the overshoot effects of LIE, this paper proposes an illumination-aware image quality assessment, called LIE-IQA, for the enhanced low-light images.
-
22 Nov 2019 2 repositories listedIntrinsic image decomposition, which is an essential task in computer vision, aims to infer the reflectance and shading of the scene.
-
19 Jun 2025 1 repository listedHowever, the effective training strategy for multiple modules are still critical to deal with both illumination issues and information interference for self-supervised depth estimation in endoscopy.
-
1 Jan 2025 1 repository listedThe effect of the former is estimated through intrinsic image decomposition, and the region of the latter is predicted in an additional background effect control branch.
-
26 Nov 2024 1 repository listedBy leveraging scene information provided by different light source positions complementing the multi-view information, we generate pseudo-label images for reflectance and shading to guide intrinsic image decomposition…
-
20 Sep 2024 1 repository listedIntrinsic image decomposition aims to separate the surface reflectance and the effects from the illumination given a single photograph.
-
4 Sep 2024 1 repository listedModeling outdoor scenes for the synthetic 3D environment requires the recovery of reflectance/albedo information from raw images, which is an ill-posed problem due to the complicated unmodeled physics in this process…
-
25 Nov 2023 1 repository listedTo address this limitation, this study rethinks hyperspectral intrinsic image decomposition for classification tasks by introducing deep feature embedding.
-
20 Jul 2023 1 repository listedThe purpose of intrinsic decomposition is to separate an image into its albedo (reflective properties) and shading components (illumination properties).
-
29 Mar 2023 1 repository listed Syntology official (archive's flag): 22 ran · 23 ran (of which 13 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 10 where Syntology's instrument failed) · 11 unverified (of 34 harvested samples) · 34 pointer-only (licence)We showcase the effectiveness of DPFs using two substantially different tasks: high-level semantic parsing and low-level intrinsic image decomposition.
-
20 Mar 2023 1 repository listedIntrinsic image decomposition (IID) is the task that decomposes a natural image into albedo and shade.
-
9 Dec 2022 1 repository listedThese instances all share the same intrinsics, but appear different due to a combination of variance within these intrinsics and differences in extrinsic factors, such as pose and illumination.
-
27 Nov 2022 1 repository listedTo further enforce the reflectance layer to be independent of shadows and specularities in the second-stage refinement, we introduce an S-Aware network that distinguishes the reflectance image from the input image.
-
30 Aug 2022 1 repository listedAn ablation study is conducted showing that the use of the proposed priors and progressive CNN increase the IID performance.
-
4 May 2022 1 repository listedWe develop a method termed ShoeRinsics that learns to predict depth by leveraging a mix of fully supervised synthetic data and unsupervised retail image data.
-
30 Mar 2022 1 repository listedAn extensive ablation study and large scale experiments are conducted showing that it is beneficial for edge-driven hybrid IID networks to make use of illumination invariant descriptors and that separating global and…
-
15 Sep 2021 1 repository listedIn this paper, firstly, we propose a new complementary feature enhanced framework, in which the complementary features are learned by several complementary subtasks and then together serve to boost the performance of…
-
1 Jul 2021 1 repository listedWe illustrate that all losses can be reduced without the necessity of taking an intrinsic image decomposition under the well-known spatial-varying illumination illumination-invariant reflectance prior knowledge.
-
5 May 2021 1 repository listedWhile our proposed method applies to both one-to-one and any-to-any relighting problems, for each case we introduce problem-specific components that enrich the model performance: 1) For one-to-one relighting we…
-
12 Feb 2021 1 repository listedIn this paper we show how to perform scene-level inverse rendering to recover shape, reflectance and lighting from a single, uncontrolled image using a fully convolutional neural network.
-
29 Nov 2020 1 repository listedHowever, document shadow or shading removal results still suffer because: (a) prior methods rely on uniformity of local color statistics, which limit their application on real-scenarios with complex document shapes and…
-
9 Dec 2019 1 repository listedThe aim is to distinguish strong photometric effects from reflectance variations.
-
1 Aug 2018 1 repository listedOur method takes the original unprocessed and per-frame processed videos as inputs to produce a temporally consistent video.
-
31 Jul 2018 1 repository listedTo that end, we propose a supervised end-to-end CNN architecture to jointly learn intrinsic image decomposition and semantic segmentation.
-
2 Apr 2018 1 repository listedHowever, it is difficult to collect ground truth training data at scale for intrinsic images.
-
21 Mar 2016 1 repository listedWe present a method for jointly predicting a depth map and intrinsic images from single-image input.
-
Objective, Absolute and Hue-aware Metrics for Intrinsic Image Decomposition on Real-World Scenes: A Proof of Concept26 May 2025 0 repositories listedIntrinsic image decomposition (IID) is the task of separating an image into albedo and shade.
-
SAIL: Self-supervised Albedo Estimation from Real Images with a Latent Diffusion Model26 May 2025 0 repositories listedIntrinsic image decomposition aims at separating an image into its underlying albedo and shading components, isolating the base color from lighting effects to enable downstream applications such as virtual relighting…
-
PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling19 Apr 2025 0 repositories listed
-
Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces28 Mar 2025 0 repositories listed
-
Single-image Reflectance and Transmittance Estimation from Any Flatbed Scanner20 Feb 2025 0 repositories listed
-
Unsupervised Intrinsic Image Decomposition with LiDAR Intensity Enhanced Training21 Mar 2024 0 repositories listed
-
Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow31 Jan 2024 0 repositories listed
-
A Theory of Joint Light and Heat Transport for Lambertian Scenes1 Jan 2024 0 repositories listed
-
Measured Albedo in the Wild: Filling the Gap in Intrinsics Evaluation27 Jun 2023 0 repositories listed
-
JoIN: Joint GANs Inversion for Intrinsic Image Decomposition18 May 2023 0 repositories listed
-
Complementary Intrinsics From Neural Radiance Fields and CNNs for Outdoor Scene Relighting1 Jan 2023 0 repositories listed
-
Light Source Separation and Intrinsic Image Decomposition Under AC Illumination1 Jan 2023 0 repositories listed
-
Discriminative feature encoding for intrinsic image decomposition25 Sep 2022 0 repositories listed
-
A Novel Intrinsic Image Decomposition Method to Recover Albedo for Aerial Images in Photogrammetry Processing8 Apr 2022 0 repositories listed
-
Invariant Descriptors for Intrinsic Reflectance Optimization8 Apr 2022 0 repositories listed
-
A Survey on Intrinsic Images: Delving Deep Into Lambert and Beyond7 Dec 2021 0 repositories listed
-
Learning Intrinsic Images for Clothing16 Nov 2021 0 repositories listed
-
Self-Supervised Intrinsic Image Decomposition Network Considering Reflectance Consistency5 Nov 2021 0 repositories listed
-
An Optical physics inspired CNN approach for intrinsic image decomposition21 May 2021 0 repositories listed
-
DeRenderNet: Intrinsic Image Decomposition of Urban Scenes with Shape-(In)dependent Shading Rendering28 Apr 2021 0 repositories listed
-
Intrinsic Image Decomposition using Paradigms20 Nov 2020 0 repositories listed
-
A deep learning based interactive sketching system for fashion images design9 Oct 2020 0 repositories listed
-
3 Sep 2020 0 repositories listed
-
Towards Geometry Guided Neural Relighting with Flash Photography12 Aug 2020 0 repositories listed
-
Learning to Factorize and Relight a City6 Aug 2020 0 repositories listed
-
Intrinsic Autoencoders for Joint Neural Rendering and Intrinsic Image Decomposition29 Jun 2020 0 repositories listed
-
Leveraging Multi-view Image Sets for Unsupervised Intrinsic Image Decomposition and Highlight Separation17 Nov 2019 0 repositories listed
-
GLoSH: Global-Local Spherical Harmonics for Intrinsic Image Decomposition1 Oct 2019 0 repositories listed
-
Non-Local Intrinsic Decomposition With Near-Infrared Priors1 Oct 2019 0 repositories listed
-
IntrinSeqNet: Learning to Estimate the Reflectance from Varying Illumination13 Jun 2019 0 repositories listed
-
Separate In Latent Space: Unsupervised Single Image Layer Separation3 Jun 2019 0 repositories listed
-
3D Face Mask Presentation Attack Detection Based on Intrinsic Image Analysis27 Mar 2019 0 repositories listed
-
Semantic Hierarchical Priors for Intrinsic Image Decomposition11 Feb 2019 0 repositories listed
-
Color naming guided intrinsic image decomposition23 Oct 2018 0 repositories listed
-
Consistency-aware Shading Orders Selective Fusion for Intrinsic Image Decomposition23 Oct 2018 0 repositories listed
-
Single Image Intrinsic Decomposition without a Single Intrinsic Image1 Sep 2018 0 repositories listed
-
CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering26 Aug 2018 0 repositories listed
-
Deep Hybrid Real and Synthetic Training for Intrinsic Decomposition30 Jul 2018 0 repositories listed
-
Free Supervision From Video Games1 Jun 2018 0 repositories listed
-
Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Faces1 Jun 2018 0 repositories listed
-
Intrinsic Image Transformation via Scale Space Decomposition25 May 2018 0 repositories listed
-
4 Dec 2017 0 repositories listed
-
Self-Supervised Intrinsic Image Decomposition10 Nov 2017 0 repositories listed
-
Label Denoising Adversarial Network (LDAN) for Inverse Lighting of Face Images6 Sep 2017 0 repositories listed
-
Shading Annotations in the Wild2 May 2017 0 repositories listed
-
DARN: a Deep Adversial Residual Network for Intrinsic Image Decomposition23 Dec 2016 0 repositories listed
-
Simultaneous Estimation of Near IR BRDF and Fine-Scale Surface Geometry1 Jun 2016 0 repositories listed
-
Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression8 Dec 2015 0 repositories listed
-
Intrinsic Decomposition of Image Sequences From Local Temporal Variations1 Dec 2015 0 repositories listed
-
Intrinsic Scene Decomposition From RGB-D images1 Dec 2015 0 repositories listed
-
Learning Ordinal Relationships for Mid-Level Vision1 Dec 2015 0 repositories listed
-
Constrained Structured Regression with Convolutional Neural Networks23 Nov 2015 0 repositories listed
-
Learning Data-driven Reflectance Priors for Intrinsic Image Decomposition8 Oct 2015 0 repositories listed
-
Learning Lightness From Human Judgement on Relative Reflectance1 Jun 2015 0 repositories listed
-
Shadow Removal from Single RGB-D Images1 Jun 2014 0 repositories listed
-
Single Image Layer Separation using Relative Smoothness1 Jun 2014 0 repositories listed
-
The Photometry of Intrinsic Images1 Jun 2014 0 repositories listed
Syntology lines on 3 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections