pith. sign in

arxiv: 2604.20243 · v1 · submitted 2026-04-22 · 💻 cs.CV

Bio-inspired Color Constancy: From Gray Anchoring Theory to Gray Pixel Methods

Kai-Fu Yang , Fu-Ya Luo , Yong-Jie Li This is my paper

Pith reviewed 2026-05-10 00:40 UTC · model grok-4.3

classification 💻 cs.CV
keywords color constancygray pixel detectionilluminant estimationLambertian reflectionbio-inspired visioncolor-opponent mechanisms
0
0 comments X

The pith

Illuminant estimation reduces to detecting gray anchors in early vision.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper argues that color constancy reduces to the detection of gray pixels or surfaces as anchors. This reduction draws directly from the Lambertian reflection model and biological color-opponent mechanisms to reinterpret existing gray-pixel methods such as Gray-Pixel and Grayness-Index. A simple learning-based method is then introduced that couples reflection-model constraints with feature learning. If this holds, color constancy becomes a more unified and biologically grounded computation rather than a collection of separate heuristics.

Core claim

Illuminant estimation can be reduced to the task of gray-anchor detection in early vision. Typical gray-pixel detection methods can be reinterpreted within a unified theoretical framework with the Lambertian reflection model and biological color-opponent mechanisms.

What carries the argument

Gray-anchor (pixel or surface) detection, which bridges biological color-opponent processes to practical illuminant estimation under the Lambertian model.

If this is right

  • Gray-pixel detection methods acquire a direct biological and physical grounding.
  • Learning-based color constancy can incorporate reflection constraints without additional priors.
  • Bio-inspired approaches become competitive for illuminant estimation tasks.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same anchoring logic could extend to other constancies such as lightness or size perception.
  • Performance drops on non-Lambertian surfaces would indicate where the reduction needs refinement.
  • Integration with modern feature learners could test scalability to video or dynamic lighting.

Load-bearing premise

The Lambertian reflection model together with biological color-opponent mechanisms is sufficient for real-world color constancy without extra scene-specific priors.

What would settle it

A collection of scenes with known illuminants where gray-anchor detection produces illuminant estimates that systematically deviate from human judgments or ground-truth measurements.

Figures

Figures reproduced from arXiv: 2604.20243 by Fu-Ya Luo, Kai-Fu Yang, Yong-Jie Li.

Figure 1
Figure 1. Figure 1: The general framework of bio-inspired color constancy according to the gray anchoring theory. The input signals are first transformed into [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Biological implementations of gray-pixel detection methods. [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Summarizing the development of bio-inspired color constancy methods with a timeline, including the gray-pixel family (upper part) and other [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: The Gray-Pixel Network. This network begins with three main inputs driven by the initial gray-pixel constraints and then predicts the pixel-wise [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Visualization results of the proposed GPNet. [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
read the original abstract

Color constancy is a fundamental ability of many biological visual systems and a crucial step in computer imaging systems. Bio-inspired modeling offers a promising way to elucidate the computational principles underlying color constancy and to develop efficient computational methods. However, bio-inspired methods for color constancy remain underexplored and lack a comprehensive analysis. This paper presents a comprehensive technical framework that integrates biological mechanisms, computational theory, and algorithmic implementation for bio-inspired color constancy. Specifically, we systematically revisit the computational theory of biological color constancy, which shows that illuminant estimation can be reduced to the task of gray-anchor (pixel or surface) detection in early vision. Subsequently, typical gray-pixel detection methods, including Gray-Pixel and Grayness-Index, are reinterpreted within a unified theoretical framework with the Lambertian reflection model and biological color-opponent mechanisms. Finally, we propose a simple learning-based method that couples reflection-model constraints with feature learning to explore the potential of bio-inspired color constancy based on gray-pixel detection. Extensive experiments confirm the effectiveness of gray-pixel detection for color constancy and demonstrate the potential of bio-inspired methods.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper claims that illuminant estimation can be reduced to the task of gray-anchor (pixel or surface) detection in early vision by integrating the Lambertian reflection model with biological color-opponent mechanisms. It reinterprets typical gray-pixel detection methods (Gray-Pixel and Grayness-Index) within this unified theoretical framework, proposes a simple learning-based method that couples reflection-model constraints with feature learning, and reports extensive experiments confirming the effectiveness of gray-pixel detection for color constancy.

Significance. If the central reduction holds, the work could offer a principled unification of biological mechanisms and computational color constancy methods, potentially guiding more robust algorithms that leverage early-vision gray anchoring. The reinterpretation provides theoretical coherence, and the learning-based extension demonstrates practical applicability with positive experimental outcomes. Credit is due for the systematic integration of theory, biology, and implementation, as well as for exploring bio-inspired gray-pixel approaches.

major comments (3)
  1. [§3] §3 (computational theory of biological color constancy): the reduction of illuminant estimation to gray-anchor detection is presented as a sufficient computational principle, yet no formal equivalence proof, invariance derivation, or error bounds are given for cases where the Lambertian assumption fails (e.g., specularities, inter-reflections, or absence of gray surfaces); this is load-bearing for the claim that the framework provides a complete reduction.
  2. [§4] §4 (reinterpretation of Gray-Pixel and Grayness-Index): the unified framework reinterprets these methods via the Lambertian model and color-opponent mechanisms, but the construction risks circularity because the gray-anchor assumptions appear to be shaped by the same priors already implicit in the original methods; a concrete test would be performance on scenes lacking gray surfaces or with multiple illuminants.
  3. [methods/experiments] Proposed learning-based method (methods/experiments sections): the new coupling of reflection constraints with feature learning inherits the same limitation, as no ablation or test demonstrates robustness when non-Lambertian effects or multi-illuminant conditions are present, undermining the claim that bio-inspired gray-pixel detection is broadly effective.
minor comments (2)
  1. [Abstract] The abstract states that 'extensive experiments confirm the effectiveness' but does not name the datasets, metrics, or statistical controls used, making it difficult to evaluate the reported improvements.
  2. [§2/§3] Notation for color-opponent mechanisms and gray-anchor detection could be introduced with explicit equations or references to specific biological models to improve clarity for readers outside the subfield.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive feedback and positive assessment of the work's potential to unify biological and computational approaches to color constancy. We address each major comment below with clarifications and indicate planned revisions to strengthen the manuscript.

read point-by-point responses

  1. Referee: §3 (computational theory of biological color constancy): the reduction of illuminant estimation to gray-anchor detection is presented as a sufficient computational principle, yet no formal equivalence proof, invariance derivation, or error bounds are given for cases where the Lambertian assumption fails (e.g., specularities, inter-reflections, or absence of gray surfaces); this is load-bearing for the claim that the framework provides a complete reduction.

    Authors: We appreciate the referee pointing this out. Section 3 derives the reduction by integrating the Lambertian reflection model with biological color-opponent mechanisms, showing illuminant estimation reduces to gray-anchor detection under those assumptions. This is framed as a computational principle from early vision rather than a universal mathematical equivalence. We do not provide a full formal proof or error bounds for all Lambertian violations. In revision, we will expand §3 with a new subsection explicitly discussing the assumptions, limitations in non-Lambertian cases (specularities, inter-reflections), and qualitative analysis of when the reduction holds, to better scope the claims. revision: yes

  2. Referee: §4 (reinterpretation of Gray-Pixel and Grayness-Index): the unified framework reinterprets these methods via the Lambertian model and color-opponent mechanisms, but the construction risks circularity because the gray-anchor assumptions appear to be shaped by the same priors already implicit in the original methods; a concrete test would be performance on scenes lacking gray surfaces or with multiple illuminants.

    Authors: The reinterpretation connects the methods to biological color-opponent processing, which was not the explicit basis in the original Gray-Pixel and Grayness-Index papers, providing a unifying lens rather than circular reuse of priors. While the Lambertian model is shared, the bio-inspired derivation adds theoretical coherence. To address the test suggestion, we will add analysis or experiments on scenes with minimal/absent gray surfaces and discuss multi-illuminant performance (using relevant datasets or simulations) in the revised version. revision: partial

  3. Referee: Proposed learning-based method (methods/experiments sections): the new coupling of reflection constraints with feature learning inherits the same limitation, as no ablation or test demonstrates robustness when non-Lambertian effects or multi-illuminant conditions are present, undermining the claim that bio-inspired gray-pixel detection is broadly effective.

    Authors: The learning-based method uses reflection constraints to guide gray-pixel feature learning and shows gains on standard benchmarks. We acknowledge the absence of targeted robustness tests for non-Lambertian effects and multi-illuminant conditions. In the revision, we will add ablations and sensitivity experiments (e.g., synthetic non-Lambertian perturbations or multi-illuminant data) to evaluate and delineate the method's applicability more clearly. revision: yes

Circularity Check

0 steps flagged

No significant circularity; derivation rests on external biological theory and adds independent learning stage.

full rationale

The paper revisits the computational theory of biological color constancy (presented as established) to reduce illuminant estimation to gray-anchor detection, reinterprets Gray-Pixel and Grayness-Index methods inside the Lambertian + color-opponent framework, and introduces a new learning-based method that couples reflection constraints with feature learning plus experimental validation. No quoted step equates a claimed prediction or first-principles result to its own fitted inputs or prior self-citation by construction. The reinterpretation is an organizational unification rather than a definitional loop, and the learning component supplies an independent training stage outside the gray-anchor assumptions.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

The central claim rests on the Lambertian model and color-opponent mechanisms drawn from prior biological and computer-vision literature; no new free parameters or invented entities are introduced in the abstract.

axioms (2)
  • domain assumption Lambertian reflection model accurately describes the image formation process for the scenes of interest
    Invoked to reinterpret gray-pixel methods as gray-anchor detectors
  • domain assumption Biological color-opponent mechanisms implement gray-anchor detection in early vision
    Used to reduce illuminant estimation to gray-pixel detection

pith-pipeline@v0.9.0 · 5493 in / 1201 out tokens · 22528 ms · 2026-05-10T00:40:04.098310+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

93 extracted references · 2 canonical work pages · 1 internal anchor

  1. [1]

    Color constancy,

    D. H. Foster, “Color constancy,”Vision Research, vol. 51, no. 7, pp. 674–700, 2011

    2011

  2. [2]

    Computational color constancy: Survey and experiments,

    A. Gijsenij, T. Gevers, and J. Van De Weijer, “Computational color constancy: Survey and experiments,”IEEE Transactions on Image Processing, vol. 20, no. 9, pp. 2475–2489, 2011

    2011

  3. [3]

    How does color constancy affect target recognition and instance segmentation?

    S. Xue, S. Gao, M. Tan, Z. He, and L. He, “How does color constancy affect target recognition and instance segmentation?” inProceedings of the ACM International Conference on Multimedia, 2021, pp. 5537–5545

    2021

  4. [4]

    Fc4: Fully convolutional color constancy with confidence-weighted pooling,

    Y. Hu, B. Wang, and S. Lin, “Fc4: Fully convolutional color constancy with confidence-weighted pooling,” inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 4085–4094

    2017

  5. [5]

    Cascading convolutional color constancy,

    H. Yu, K. Chen, K. Wang, Y. Qian, Z. Zhang, and K. Jia, “Cascading convolutional color constancy,” inProceedings of the AAAI Confer- ence on Artificial Intelligence, vol. 34, no. 07, 2020, pp. 12 725–12 732

    2020

  6. [6]

    Clcc: Contrastive learning for color con- stancy,

    Y.-C. Lo, C.-C. Chang, H.-C. Chiu, Y.-H. Huang, C.-P . Chen, Y.- L. Chang, and K. Jou, “Clcc: Contrastive learning for color con- stancy,” inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021, pp. 8053–8063

    2021

  7. [7]

    Cross- camera convolutional color constancy,

    M. Afifi, J. T. Barron, C. LeGendre, Y.-T. Tsai, and F. Bleibel, “Cross- camera convolutional color constancy,” inProceedings of the IEEE International Conference on Computer Vision, 2021, pp. 1981–1990

    2021

  8. [8]

    Lightness and retinex theory,

    E. H. Land and J. J. McCann, “Lightness and retinex theory,” Journal of the Optical Society of America, vol. 61, no. 1, pp. 1–11, 1971

    1971

  9. [9]

    Color contrast: a contributory mecha- nism to color constancy,

    A. Hurlbert and K. Wolf, “Color contrast: a contributory mecha- nism to color constancy,”Progress in Brain Research, vol. 144, pp. 145–160, 2004

    2004

  10. [10]

    The goldfish—a colour-constant ani- mal,

    S. D ¨orr and C. Neumeyer, “The goldfish—a colour-constant ani- mal,”Perception, vol. 25, no. 2, pp. 243–250, 1996

    1996

  11. [11]

    Color constancy in the honeybee,

    A. Werner, R. Menzel, and C. Wehrhahn, “Color constancy in the honeybee,”Journal of Neuroscience, vol. 8, no. 1, pp. 156–159, 1988

    1988

  12. [12]

    Cortical mechanisms of colour vision,

    K. R. Gegenfurtner, “Cortical mechanisms of colour vision,”Nature Reviews Neuroscience, vol. 4, no. 7, pp. 563–572, 2003

    2003

  13. [13]

    Colour vision: primary visual cortex shows its influence,

    A. Hurlbert, “Colour vision: primary visual cortex shows its influence,”Current Biology, vol. 13, no. 7, pp. R270–R272, 2003

    2003

  14. [14]

    Color in the cortex: single-and double-opponent cells,

    R. Shapley and M. J. Hawken, “Color in the cortex: single-and double-opponent cells,”Vision Research, vol. 51, no. 7, pp. 701–717, 2011

    2011

  15. [15]

    A color constancy model with double-opponency mechanisms,

    S. Gao, K. Yang, C. Li, and Y. Li, “A color constancy model with double-opponency mechanisms,” inProceedings of the IEEE International Conference on Computer Vision, 2013, pp. 929–936

    2013

  16. [16]

    Color constancy using double-opponency,

    S.-B. Gao, K.-F. Yang, C.-Y. Li, and Y.-J. Li, “Color constancy using double-opponency,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 10, pp. 1973–1985, 2015

    1973

  17. [17]

    Gray Anchoring: a New Computational Theory for Biological Color Constancy

    K.-F. Yang, D. Xing, and Y.-J. Li, “Gray anchoring: a new com- putational theory for biological color constancy,”arXiv preprint arXiv:2410.08823, 2026

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  18. [18]

    Efficient illuminant estimation for color constancy using grey pixels,

    K.-F. Yang, S.-B. Gao, and Y.-J. Li, “Efficient illuminant estimation for color constancy using grey pixels,” inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 2254–2263

    2015

  19. [19]

    On finding gray pixels,

    Y. Qian, J.-K. Kamarainen, J. Nikkanen, and J. Matas, “On finding gray pixels,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 8062–8070

    2019

  20. [20]

    Color ap- pearance of familiar objects: Effects of object shape, texture, and illumination changes,

    M. Olkkonen, T. Hansen, and K. R. Gegenfurtner, “Color ap- pearance of familiar objects: Effects of object shape, texture, and illumination changes,”Journal of Vision, vol. 8, no. 5, pp. 1–13, 2008

    2008

  21. [21]

    Color scaling of discs and natural objects at different luminance levels,

    T. Hansen and K. R. Gegenfurtner, “Color scaling of discs and natural objects at different luminance levels,”Visual Neuroscience, vol. 23, no. 3-4, pp. 603–610, 2006

    2006

  22. [22]

    Learning to adapt to light,

    K.-F. Yang, C. Cheng, S.-X. Zhao, H.-M. Yan, X.-S. Zhang, and Y.-J. Li, “Learning to adapt to light,”International Journal of Computer Vision, vol. 131, no. 4, pp. 1022–1041, 2023

    2023

  23. [23]

    A spatial processor model for object colour per- ception,

    G. Buchsbaum, “A spatial processor model for object colour per- ception,”Journal of the Franklin institute, vol. 310, no. 1, pp. 1–26, 1980

    1980

  24. [24]

    Formal connections between lightness algorithms,

    A. Hurlbert, “Formal connections between lightness algorithms,” Journal of the Optical Society of America A, vol. 3, no. 10, pp. 1684– 1693, 1986

    1986

  25. [25]

    Edge-based color constancy,

    J. Van De Weijer, T. Gevers, and A. Gijsenij, “Edge-based color constancy,”IEEE Transactions on Image Processing, vol. 16, no. 9, pp. 2207–2214, 2007

    2007

  26. [26]

    Shades of gray and colour con- stancy,

    G. D. Finlayson and E. Trezzi, “Shades of gray and colour con- stancy,” inColor and Imaging Conference, vol. 12. Society of Imaging Science and Technology, 2004, pp. 37–41

    2004

  27. [27]

    Solving for colour constancy using a constrained dichromatic reflection model,

    G. D. Finlayson and G. Schaefer, “Solving for colour constancy using a constrained dichromatic reflection model,”International Journal of Computer Vision, vol. 42, no. 3, pp. 127–144, 2001

    2001

  28. [28]

    Dichromatic illumination estimation without pre- segmentation,

    J. Toro, “Dichromatic illumination estimation without pre- segmentation,”Pattern Recognition Letters, vol. 29, no. 7, pp. 871– 877, 2008

    2008

  29. [29]

    Method for computing the scene-illuminant chro- maticity from specular highlights,

    H.-C. Lee, “Method for computing the scene-illuminant chro- maticity from specular highlights,”Journal of the Optical Society of America A, vol. 3, no. 10, pp. 1694–1699, 1986

    1986

  30. [30]

    Estimating spectral reflectance using highlights,

    G. Healey, “Estimating spectral reflectance using highlights,”Im- age and vision computing, vol. 9, no. 5, pp. 333–337, 1991

    1991

  31. [31]

    Color constancy through inverse-intensity chromaticity space,

    R. T. Tan, K. Nishino, and K. Ikeuchi, “Color constancy through inverse-intensity chromaticity space,”Journal of the Optical Society of America A, vol. 21, no. 3, pp. 321–334, 2004

    2004

  32. [32]

    Committee-based color constancy,

    V . C. Cardei and B. Funt, “Committee-based color constancy,” in Color and Imaging Conference, vol. 1999, no. 1. Society for Imaging Science and Technology, 1999, pp. 311–313

    1999

  33. [33]

    Consensus-based frame- work for illuminant chromaticity estimation,

    S. Bianco, F. Gasparini, and R. Schettini, “Consensus-based frame- work for illuminant chromaticity estimation,”Journal of Electronic Imaging, vol. 17, no. 2, p. 023013, 2008

    2008

  34. [34]

    A combined physical and statistical approach to colour constancy,

    G. Schaefer, S. Hordley, and G. Finlayson, “A combined physical and statistical approach to colour constancy,” inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2005, pp. 148–153

    2005

  35. [35]

    Corrected-moment illuminant estimation,

    G. D. Finlayson, “Corrected-moment illuminant estimation,” in Proceedings of the IEEE International Conference on Computer Vision. IEEE, 2013, pp. 1904–1911

    2013

  36. [36]

    Automatic color constancy algorithm selection and combination,

    S. Bianco, G. Ciocca, C. Cusano, and R. Schettini, “Automatic color constancy algorithm selection and combination,”Pattern Recognition, vol. 43, no. 3, pp. 695–705, 2010

    2010

  37. [37]

    Adaptive color constancy using faces,

    S. Bianco and R. Schettini, “Adaptive color constancy using faces,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 8, pp. 1505–1518, 2014. YANG, ET AL. 12

    2014

  38. [38]

    Using high-level visual information for color constancy,

    J. Van De Weijer, C. Schmid, and J. Verbeek, “Using high-level visual information for color constancy,” inProceedings of the IEEE International Conference on Computer Vision. IEEE, 2007, pp. 1–8

    2007

  39. [39]

    Color constancy using natural image statistics and scene semantics,

    A. Gijsenij and T. Gevers, “Color constancy using natural image statistics and scene semantics,”IEEE Transactions on Pattern Anal- ysis and Machine Intelligence, vol. 33, no. 4, pp. 687–698, 2011

    2011

  40. [40]

    A novel algorithm for color constancy,

    D. A. Forsyth, “A novel algorithm for color constancy,”Interna- tional Journal of Computer Vision, vol. 5, no. 1, pp. 5–35, 1990

    1990

  41. [41]

    Improvements to gamut mapping colour constancy algorithms,

    K. Barnard, “Improvements to gamut mapping colour constancy algorithms,” inEuropean Conference on Computer Vision. Springer, 2000, pp. 390–403

    2000

  42. [42]

    Generalized gamut mapping using image derivative structures for color constancy,

    A. Gijsenij, T. Gevers, and J. Van De Weijer, “Generalized gamut mapping using image derivative structures for color constancy,” International Journal of Computer Vision, vol. 86, no. 2, pp. 127–139, 2010

    2010

  43. [43]

    Estimating illumination chromaticity via support vector regression

    B. Funt and W. Xiong, “Estimating illumination chromaticity via support vector regression.” Color and Imaging Conference, 2004

    2004

  44. [44]

    Effective learning- based illuminant estimation using simple features,

    D. Cheng, B. Price, S. Cohen, and M. S. Brown, “Effective learning- based illuminant estimation using simple features,” inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1000–1008

    2015

  45. [45]

    Deep structured-output regression learning for computational color constancy,

    Y. Qian, K. Chen, J.-K. K ¨am¨ar¨ainen, J. Nikkanen, and J. Matas, “Deep structured-output regression learning for computational color constancy,” inProceedings of the International Conference on Pattern Recognition. IEEE, 2016, pp. 1899–1904

    2016

  46. [46]

    Color constancy using cnns,

    S. Bianco, C. Cusano, and R. Schettini, “Color constancy using cnns,” inProceedings of the IEEE conference on computer vision and pattern recognition workshops, 2015, pp. 81–89

    2015

  47. [47]

    Color constancy by deep learning,

    Z. Lou, T. Gevers, N. Hu, M. P . Lucassenet al., “Color constancy by deep learning,” inBMVC, vol. 2, 2015, p. 3

    2015

  48. [48]

    Deep specialized network for illuminant estimation,

    W. Shi, C. C. Loy, and X. Tang, “Deep specialized network for illuminant estimation,” inEuropean Conference on Computer Vision. Springer, 2016, pp. 371–387

    2016

  49. [49]

    Single and multiple illuminant estimation using convolutional neural networks,

    S. Bianco, C. Cusano, and R. Schettini, “Single and multiple illuminant estimation using convolutional neural networks,”IEEE Transactions on Image Processing, vol. 26, no. 9, pp. 4347–4362, 2017

    2017

  50. [50]

    Convolutional color constancy,

    J. T. Barron, “Convolutional color constancy,” inProceedings of the IEEE International Conference on Computer Vision, 2015, pp. 379–387

    2015

  51. [51]

    Fast fourier color constancy,

    J. T. Barron and Y.-T. Tsai, “Fast fourier color constancy,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 886–894

    2017

  52. [52]

    Integral fast fourier color constancy,

    W. Wei, Y. Qian, H. Chen, J. Dai, and Y. Jin, “Integral fast fourier color constancy,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 2025, pp. 26 420– 26 429

    2025

  53. [53]

    The retinex,

    E. H. Lamd, “The retinex,”American Scientist, vol. 52, no. 2, pp. 247–264, 1964

    1964

  54. [54]

    A retinal mechanism inspired color constancy model,

    X.-S. Zhang, S.-B. Gao, R.-X. Li, X.-Y. Du, C.-Y. Li, and Y.-J. Li, “A retinal mechanism inspired color constancy model,”IEEE Transactions on Image Processing, vol. 25, no. 3, pp. 1219–1232, 2016

    2016

  55. [55]

    Colour constancy beyond the classical receptive field,

    A. Akbarinia and C. A. Parraga, “Colour constancy beyond the classical receptive field,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 40, no. 9, pp. 2081–2094, 2017

    2081

  56. [56]

    Bio-cc: Biologically inspired color constancy

    O. Ulucan, D. Ulucan, and M. Ebner, “Bio-cc: Biologically inspired color constancy.” inBMVC, 2022, p. 960

    2022

  57. [57]

    Relational colour constancy from invariant cone-excitation ratios,

    D. H. Foster and S. M. Nascimento, “Relational colour constancy from invariant cone-excitation ratios,”Proceedings of the Royal Society of London. Series B: Biological Sciences, vol. 257, no. 1349, pp. 115–121, 1994

    1994

  58. [58]

    Horizon- tal cells reveal cone type-specific adaptation in primate retina,

    B. B. Lee, D. M. Dacey, V . C. Smith, and J. Pokorny, “Horizon- tal cells reveal cone type-specific adaptation in primate retina,” Proceedings of the National Academy of Sciences, vol. 96, no. 25, pp. 14 611–14 616, 1999

    1999

  59. [59]

    Spatial structure of cone inputs to color cells in alert macaque primary visual cortex (v-1),

    B. R. Conway, “Spatial structure of cone inputs to color cells in alert macaque primary visual cortex (v-1),”Journal of Neuroscience, vol. 21, no. 8, pp. 2768–2783, 2001

    2001

  60. [60]

    Spatial and temporal properties of cone signals in alert macaque primary visual cortex,

    B. R. Conway and M. S. Livingstone, “Spatial and temporal properties of cone signals in alert macaque primary visual cortex,” Journal of Neuroscience, vol. 26, no. 42, pp. 10 826–10 846, 2006

    2006

  61. [61]

    Colour coding in the cerebral cortex: the reaction of cells in monkey visual cortex to wavelengths and colours,

    S. Zeki, “Colour coding in the cerebral cortex: the reaction of cells in monkey visual cortex to wavelengths and colours,”Neuro- science, vol. 9, no. 4, pp. 741–765, 1983

    1983

  62. [62]

    Primate cor- tical area v4 important for colour constancy but not wavelength discrimination,

    H. Wild, S. Butler, D. Carden, and J. Kulikowski, “Primate cor- tical area v4 important for colour constancy but not wavelength discrimination,”Nature, vol. 313, no. 5998, pp. 133–135, 1985

    1985

  63. [63]

    The effects of v4 lesions on the visual abilities of macaques: hue discrimination and colour constancy,

    V . Walsh, D. Carden, S. Butler, and J. Kulikowski, “The effects of v4 lesions on the visual abilities of macaques: hue discrimination and colour constancy,”Behavioural Brain Research, vol. 53, no. 1-2, pp. 51–62, 1993

    1993

  64. [64]

    Color perception: Objects, constancy, and categories,

    C. Witzel and K. R. Gegenfurtner, “Color perception: Objects, constancy, and categories,”Annual review of vision science, vol. 4, no. 1, pp. 475–499, 2018

    2018

  65. [65]

    The role of bright pixels in illumination estimation,

    H. R. V . Joze, M. S. Drew, G. D. Finlayson, and P . A. T. Rey, “The role of bright pixels in illumination estimation,” inColor and Imaging Conference, vol. 20. Society of Imaging Science and Technology, 2012, pp. 41–46

    2012

  66. [66]

    Quasi-unsupervised color constancy,

    S. Bianco and C. Cusano, “Quasi-unsupervised color constancy,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 12 212–12 221

    2019

  67. [67]

    Marr,Vision: A computational investigation into the human repre- sentation and processing of visual information

    D. Marr,Vision: A computational investigation into the human repre- sentation and processing of visual information. MIT press, 2010

    2010

  68. [68]

    Elements of psychophysics. vol. i. henry holt editions in psychology,

    G. Fechner, “Elements of psychophysics. vol. i. henry holt editions in psychology,” 1966

    1966

  69. [69]

    Automatic white balancing via gray surface identification,

    W. Xiong, B. Funt, L. Shi, S.-S. Kim, B.-H. Kang, S.-D. Lee, and C.-Y. Kim, “Automatic white balancing via gray surface identification,” inColor and Imaging Conference, vol. 15. Society of Imaging Science and Technology, 2007, pp. 143–146

    2007

  70. [70]

    Color constancy using achromatic surface,

    B. Li, D. Xu, W. Xiong, and S. Feng, “Color constancy using achromatic surface,”Color Research & Application, vol. 35, no. 4, pp. 304–312, 2010

    2010

  71. [71]

    Degree- of-linear-polarization-based color constancy,

    T. Ono, Y. Kondo, L. Sun, T. Kurita, and Y. Moriuchi, “Degree- of-linear-polarization-based color constancy,” inProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 19 740–19 749

    2022

  72. [72]

    Nighttime color constancy using robust gray pixels,

    C. Cheng, K.-F. Yang, X.-M. Wan, L. L. H. Chan, and Y.-J. Li, “Nighttime color constancy using robust gray pixels,”Journal of the Optical Society of America A, vol. 41, no. 3, pp. 476–488, 2024

    2024

  73. [73]

    Improved single-illumination esti- mation accuracy via redefining the illuminant-invariant descriptor and the grey pixels,

    X. Yang, X. Jin, and J. Zhang, “Improved single-illumination esti- mation accuracy via redefining the illuminant-invariant descriptor and the grey pixels,”Optics Express, vol. 26, no. 22, pp. 29 055– 29 067, 2018

    2018

  74. [74]

    Discharge patterns and functional organization of mammalian retina,

    S. W. Kuffler, “Discharge patterns and functional organization of mammalian retina,”Journal of Neurophysiology, vol. 16, no. 1, pp. 37–68, 1953

    1953

  75. [75]

    Spatial and chromatic interactions in the lateral geniculate body of the rhesus monkey

    T. N. Wiesel and D. H. Hubel, “Spatial and chromatic interactions in the lateral geniculate body of the rhesus monkey.”Journal of Neurophysiology, vol. 29, no. 6, pp. 1115–1156, 1966

    1966

  76. [76]

    INTEL-TAU: A color constancy dataset,

    F. Laakom, J. Raitoharju, J. Nikkanen, A. Iosifidis, and M. Gabbouj, “INTEL-TAU: A color constancy dataset,”IEEE Access, vol. 9, pp. 39 560–39 567, 2021

    2021

  77. [77]

    Rehabilitating the colorchecker dataset for illuminant estimation,

    G. Hemrit, G. D. Finlayson, A. Gijsenij, P . Gehler, S. Bianco, B. Funt, M. Drew, and L. Shi, “Rehabilitating the colorchecker dataset for illuminant estimation,” inColor and Imaging Conference. Society for Imaging Science and Technology, 2018, pp. 350–353

    2018

  78. [78]

    Providing a single ground- truth for illuminant estimation for the colorchecker dataset,

    G. Hemrit, G. D. Finlayson, A. Gijsenij, P . Gehler, S. Bianco, M. S. Drew, B. Funt, and L. Shi, “Providing a single ground- truth for illuminant estimation for the colorchecker dataset,”IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 5, pp. 1286–1287, 2019

    2019

  79. [79]

    Re-processed version of the gehler color constancy dataset of 568 images,

    L. Shi and B. Funt, “Re-processed version of the gehler color constancy dataset of 568 images,” 2010, accessed from https: //www2.cs.sfu.ca/∼colour/data/

    2010

  80. [80]

    A comparison of computational color constancy algorithms. ii. experiments with image data,

    K. Barnard, L. Martin, A. Coath, and B. Funt, “A comparison of computational color constancy algorithms. ii. experiments with image data,”IEEE Transactions on Image Processing, vol. 11, no. 9, pp. 985–996, 2002

    2002

Showing first 80 references.