Browse State-of-the-Art › Color Constancy

Color Constancy

40 papers with code · 1 benchmark · 5 datasets archive 2025-07-28

Computer Vision

Color Constancy is the ability of the human vision system to perceive the colors of the objects in the scene largely invariant to the color of the light source. The task of computational Color Constancy is to estimate the scene illumination and then perform the chromatic adaptation in order to remove the influence of the illumination color on the colors of the objects in the scene.

Source: CroP: Color Constancy Benchmark Dataset Generator

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each 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 instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” 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.

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

5 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Papers archive 2025-07-28

archive papers tagged: 102 · with a code link: 40 · where Syntology ran a sample: 2 (2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (2 of 102 tagged: 2 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 2: papers 1 to 100 of 102, 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.

  • The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network.
  • 8 Mar 2020 3 repositories listed
    The conventional approach is to use a single frame - shot frame - to estimate the scene illumination color.
  • 23 Nov 2016 2 repositories listed
    We present Fast Fourier Color Constancy (FFCC), a color constancy algorithm which solves illuminant estimation by reducing it to a spatial localization task on a torus.
  • 10 Apr 2025 1 repository listed
    Our method leverages pre-calibrated color correction matrices (CCMs) available on ISPs that map the camera's raw color space to a standard space (e. g., CIE XYZ).
  • 20 Sep 2024 1 repository listed
    Intrinsic image decomposition aims to separate the surface reflectance and the effects from the illumination given a single photograph.
  • 5 Aug 2024 1 repository listed
    While deep learning-based computer-aided diagnosis for skin lesion image analysis is approaching dermatologists' performance levels, there are several works showing that incorporating additional features such as shape…
  • 17 Apr 2024 1 repository listed
    First, we propose a novel module that can be integrated into any neural ISP to capture the global context information from the full RAW images.
  • 11 Apr 2024 1 repository listed
    Color constancy (CC) describes the ability of the visual system to perceive an object as having a relatively constant color despite changes in lighting conditions.
  • 5 Feb 2024 1 repository listed
    Motivated by this, we propose a novel multi-illuminant color constancy method, by learning pixel-wise illumination maps caused by multiple light sources.
  • 10 Jan 2022 1 repository listed
    Digital cameras transform sensor RAW readings into RGB images by means of their Image Signal Processor (ISP).
  • 22 Nov 2021 1 repository listed
    In this paper, we present Point Cloud Color Constancy, in short PCCC, an illumination chromaticity estimation algorithm exploiting a point cloud.
  • 10 Nov 2021 1 repository listed
    We test this approach on the proposed method and show that it can indeed be used to avoid several extreme error cases and, thus, improves the practicality of the proposed technique.
  • 9 Jun 2021 1 repository listed
    In this paper, we present CLCC, a novel contrastive learning framework for color constancy.
  • 1 Jan 2021 1 repository listed
    STAR is a general architecture that can be easily adapted to different image enhancement tasks.
  • 28 Dec 2020 1 repository listed
    High levels of color constancy were achieved with different DNN architectures.
  • 24 Nov 2020 1 repository listed
    We present "Cross-Camera Convolutional Color Constancy" (C5), a learning-based method, trained on images from multiple cameras, that accurately estimates a scene's illuminant color from raw images captured by a new…
  • 19 Nov 2020 1 repository listed
    In this paper, a new illumination estimation dataset is proposed that aims to alleviate many of the mentioned problems and to help the illumination estimation research.
  • 21 Sep 2020 1 repository listed
    Hazy environment attenuates the scene radiance and causes difficulty in distinguishing the color and texture of the scene.
  • 1 Jun 2020 1 repository listed
    Given a new unseen device with limited number of training samples, our method is capable of delivering accurate color constancy by merely learning the camera-specific parameters from the few-shot dataset.
  • 28 Feb 2020 1 repository listed
    Firstly, we select a set of candidate scene illuminants in a data-driven fashion and apply them to a target image to generate of set of corrected images.
  • 24 Dec 2019 1 repository listed
    Regressing the illumination of a scene from the representations of object appearances is popularly adopted in computational color constancy.
  • There is active research targeting local image manipulations that can fool deep neural networks (DNNs) into producing incorrect results.
  • 23 Oct 2019 1 repository listed
    In this paper, we describe a new large dataset for illumination estimation.
  • 11 Jun 2019 1 repository listed
    To further improve the illumination estimation accuracy, we propose a novel attention mechanism for the BoCF model with two variants based on self-attention.
  • 1 Jun 2019 1 repository listed
    In particular, we show that CNNs trained for image denoising, image deblurring, and computational color constancy are able to replicate the human response to visual illusions, and that the extent of this replication…
  • 1 Jun 2019 1 repository listed
    After training, unbalanced images can be processed thanks to the preliminary conversion to grayscale of the input to the neural network.
  • 1 Jun 2019 1 repository listed
    The challenge lies not in identifying what the correct white balance should have been, but in the fact that the in-camera white-balance procedure is followed by several camera-specific nonlinear color manipulations that…
  • 12 May 2019 1 repository listed
    First, the contextual net with a center-surround architecture extracts local contextual features from image patches, and generates initial illuminant estimates and the corresponding color corrected patches.
  • 1 Apr 2019 1 repository listed
    Long-term metric self-localization is an essential capability of autonomous mobile robots, but remains challenging for vision-based systems due to appearance changes caused by lighting, weather, or seasonal variations.
  • 6 Dec 2018 1 repository listed
    Achieving color constancy between and within images, i. e., minimizing the color difference between the same object imaged under nonuniform and varied illuminations is crucial for computer vision tasks such as…
  • 4 Dec 2018 1 repository listed
  • 20 Nov 2018 1 repository listed
  • 15 Nov 2018 1 repository listed
  • 18 Oct 2018 1 repository listed
  • 25 Jun 2018 1 repository listed
  • 22 Mar 2018 1 repository listed
  • 1 Feb 2018 1 repository listed
  • 1 Jul 2017 1 repository listed
  • 2 Jul 2015 1 repository listed
  • 17 Apr 2015 1 repository listed
  • A Poisson-Guided Decomposition Network for Extreme Low-Light Image Enhancement
    4 Jun 2025 0 repositories listed
  • GCC: Generative Color Constancy via Diffusing a Color Checker
    24 Feb 2025 0 repositories listed
  • Integral Fast Fourier Color Constancy
    5 Feb 2025 0 repositories listed
  • Multi-illuminant Color Constancy via Multi-scale Illuminant Estimation and Fusion
    4 Feb 2025 0 repositories listed
  • Primary visual cortex contributes to color constancy by predicting rather than discounting the illuminant: evidence from a computational study
    10 Dec 2024 0 repositories listed
  • Double opponency serves as a basis for color constancy
    11 Oct 2024 0 repositories listed
  • Optimizing Illuminant Estimation in Dual-Exposure HDR Imaging
    4 Mar 2024 0 repositories listed
  • NightCC: Nighttime Color Constancy via Adaptive Channel Masking
    1 Jan 2024 0 repositories listed
  • Investigating Color Illusions from the Perspective of Computational Color Constancy
    20 Dec 2023 0 repositories listed
  • Practical cross-sensor color constancy using a dual-mapping strategy
    20 Nov 2023 0 repositories listed
  • Fooling Polarization-based Vision using Locally Controllable Polarizing Projection
    31 Mar 2023 0 repositories listed
  • MIMT: Multi-Illuminant Color Constancy via Multi-Task Local Surface and Light Color Learning
    16 Nov 2022 0 repositories listed
  • Template matching with white balance adjustment under multiple illuminants
    3 Aug 2022 0 repositories listed
  • Dynamic Dense RGB-D SLAM using Learning-based Visual Odometry
    12 May 2022 0 repositories listed
  • Designing Perceptual Puzzles by Differentiating Probabilistic Programs
    26 Apr 2022 0 repositories listed
  • Learning Enriched Illuminants for Cross and Single Sensor Color Constancy
    21 Mar 2022 0 repositories listed
  • Degree-of-Linear-Polarization-Based Color Constancy
    1 Jan 2022 0 repositories listed
  • Generative Models for Multi-Illumination Color Constancy
    2 Sep 2021 0 repositories listed
  • Multi-color balance for color constancy
    21 May 2021 0 repositories listed
  • Illumination Estimation Challenge: experience of past two years
    31 Dec 2020 0 repositories listed
  • Underwater Image Color Correction by Complementary Adaptation
    21 Oct 2020 0 repositories listed
  • Shape, Illumination, and Reflectance from Shading
    7 Oct 2020 0 repositories listed
  • Monte Carlo Dropout Ensembles for Robust Illumination Estimation
    20 Jul 2020 0 repositories listed
  • End-to-End Illuminant Estimation Based on Deep Metric Learning
    1 Jun 2020 0 repositories listed
  • Probabilistic Color Constancy
    6 May 2020 0 repositories listed
  • Investigating the Importance of Shape Features, Color Constancy, Color Spaces and Similarity Measures in Open-Ended 3D Object Recognition
    10 Feb 2020 0 repositories listed
  • ADCC: An Effective and Intelligent Attention Dense Color Constancy System for Studying Images in Smart Cities
    17 Nov 2019 0 repositories listed
  • Fast Color Constancy with Patch-wise Bright Pixels
    17 Nov 2019 0 repositories listed
  • Fast Fourier Color Constancy and Grayness Index for ISPA Illumination Estimation Challenge
    6 Aug 2019 0 repositories listed
  • Color Cerberus
    15 Jul 2019 0 repositories listed
  • Illuminant Chromaticity Estimation from Interreflections
    13 Jun 2019 0 repositories listed
  • Color Constancy Convolutional Autoencoder
    4 Jun 2019 0 repositories listed
  • Dichromatic Model Based Temporal Color Constancy for AC Light Sources
    1 Jun 2019 0 repositories listed
  • CroP: Color Constancy Benchmark Dataset Generator
    29 Mar 2019 0 repositories listed
  • The Past and the Present of the Color Checker Dataset Misuse
    11 Mar 2019 0 repositories listed
  • Color Constancy by GANs: An Experimental Survey
    7 Dec 2018 0 repositories listed
  • Formulating Camera-Adaptive Color Constancy as a Few-shot Meta-Learning Problem
    28 Nov 2018 0 repositories listed
  • Convolutional Neural Networks Deceived by Visual Illusions
    26 Nov 2018 0 repositories listed
  • Color naming guided intrinsic image decomposition
    23 Oct 2018 0 repositories listed
  • Learning Illuminant Estimation from Object Recognition
    23 May 2018 0 repositories listed
  • Green Stability Assumption: Unsupervised Learning for Statistics-Based Illumination Estimation
    2 Feb 2018 0 repositories listed
  • Fully Point-wise Convolutional Neural Network for Modeling Statistical Regularities in Natural Images
    19 Jan 2018 0 repositories listed
  • Unsupervised Learning for Color Constancy
    1 Dec 2017 0 repositories listed
  • Recurrent Color Constancy
    1 Oct 2017 0 repositories listed
  • A Lightweight Approach for On-the-Fly Reflectance Estimation
    19 May 2017 0 repositories listed
  • INTEL-TUT Dataset for Camera Invariant Color Constancy Research
    21 Mar 2017 0 repositories listed
  • Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis
    10 Mar 2017 0 repositories listed
  • Functions that Emerge through End-to-End Reinforcement Learning - The Direction for Artificial General Intelligence -
    7 Mar 2017 0 repositories listed
  • Automated Linear-Time Detection and Quality Assessment of Superpixels in Uncalibrated True- or False-Color RGB Images
    8 Jan 2017 0 repositories listed
  • Color Constancy with Derivative Colors
    25 Nov 2016 0 repositories listed
  • Improving Color Constancy by Discounting the Variation of Camera Spectral Sensitivity
    6 Sep 2016 0 repositories listed
  • Approaching the Computational Color Constancy as a Classification Problem through Deep Learning
    29 Aug 2016 0 repositories listed
  • Deep Structured-Output Regression Learning for Computational Color Constancy
    13 Jul 2016 0 repositories listed
  • Amplitude Modulated Video Camera - Light Separation in Dynamic Scenes
    1 Jun 2016 0 repositories listed
  • Beyond White: Ground Truth Colors for Color Constancy Correction
    1 Dec 2015 0 repositories listed
  • Color Constancy by Learning to Predict Chromaticity from Luminance
    6 Jun 2015 0 repositories listed
  • Effective Learning-Based Illuminant Estimation Using Simple Features
    1 Jun 2015 0 repositories listed
  • Efficient Illuminant Estimation for Color Constancy Using Grey Pixels
    1 Jun 2015 0 repositories listed
  • Design of Novel Algorithm and Architecture for Gaussian Based Color Image Enhancement System for Real Time Applications
    14 Sep 2014 0 repositories listed
  • The Photometry of Intrinsic Images
    1 Jun 2014 0 repositories listed

Syntology lines on 2 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