The Past and the Present of the Color Checker Dataset Misuse

The pipelines of digital cameras contain a part for computational color constancy, which aims to remove the influence of the illumination on the scene colors. One of the best known and most widely used benchmark datasets for this problem is the Color Checker dataset. However, due to the improper handling of the black level in its images, this dataset has been widely misused and while some recent publications tried to alleviate the problem, they nevertheless erred and created additional wrong data. This paper gives a history of the Color Checker dataset usage, it describes the origins and reasons for its misuses, and it explains the old and new mistakes introduced in the most recent publications that tried to handle the issue. This should, hopefully, help to prevent similar future misuses.

[1]  Anestis Terzis,et al.  Handbook of Camera Monitor Systems: The Automotive Mirror-Replacement Technology based on ISO 16505 , 2016 .

[2]  Keigo Hirakawa,et al.  Color Constancy with Spatio-Spectral Statistics , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Sven Loncaric,et al.  Color Beaver: Bounding Illumination Estimations for Higher Accuracy , 2019, VISIGRAPP.

[4]  Cordelia Schmid,et al.  Using High-Level Visual Information for Color Constancy , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[5]  Sven Loncaric,et al.  Improving the white patch method by subsampling , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[6]  Stephen Lin,et al.  FC^4: Fully Convolutional Color Constancy with Confidence-Weighted Pooling , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Haisong Xu,et al.  PILOT: A Pixel Intensity Driven Illuminant Color Estimation Framework for Color Constancy , 2018, ArXiv.

[8]  Yun-Ta Tsai,et al.  Fast Fourier Color Constancy , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Theo Gevers,et al.  Color Constancy using Natural Image Statistics , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Joost van de Weijer,et al.  Author Manuscript, Published in "ieee Transactions on Image Processing Edge-based Color Constancy , 2022 .

[11]  Brian V. Funt,et al.  A Large Image Database for Color Constancy Research , 2003, CIC.

[12]  Sven Loncaric,et al.  Unsupervised Learning for Color Constancy , 2017, VISIGRAPP.

[13]  Sven Loncaric,et al.  Flash and Storm: Fast and Highly Practical Tone Mapping based on Naka-Rushton Equation , 2018, VISIGRAPP.

[14]  Mark S. Drew,et al.  Colour Constancy from Both Sides of the Shadow Edge , 2013, 2013 IEEE International Conference on Computer Vision Workshops.

[15]  Sven Loncaric,et al.  Using the red chromaticity for illumination estimation , 2015, 2015 9th International Symposium on Image and Signal Processing and Analysis (ISPA).

[16]  Raimondo Schettini,et al.  Color constancy using CNNs , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[17]  Sophie Triantaphillidou,et al.  The Manual of Photography , 2010 .

[18]  Sven Loncaric,et al.  Blue Shift Assumption: Improving Illumination Estimation Accuracy for Single Image from Unknown Source , 2019, VISIGRAPP.

[19]  Xiaoou Tang,et al.  Deep Specialized Network for Illuminant Estimation , 2016, ECCV.

[20]  Haisong Xu,et al.  Color Constancy by Reweighting Image Feature Maps , 2020, IEEE Transactions on Image Processing.

[21]  Graham D. Finlayson,et al.  Shades of Gray and Colour Constancy , 2004, CIC.

[22]  Sven Loncaric,et al.  Using the Random Sprays Retinex Algorithm for Global Illumination Estimation , 2013, ArXiv.

[23]  Ingeborg Tastl,et al.  Gamut Constrained Illuminant Estimation , 2006, International Journal of Computer Vision.

[24]  Sven Loncaric,et al.  Color Rabbit: Guiding the distance of local maximums in illumination estimation , 2014, 2014 19th International Conference on Digital Signal Processing.

[25]  Michael S. Brown,et al.  A Hybrid Strategy for Illuminant Estimation Targeting Hard Images , 2015, 2015 IEEE International Conference on Computer Vision Workshop (ICCVW).

[26]  Andrew Blake,et al.  Bayesian color constancy revisited , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Sven Loncaric,et al.  Color Cat: Remembering Colors for Illumination Estimation , 2015, IEEE Signal Processing Letters.

[28]  Lilong Shi,et al.  The Rehabilitation of MaxRGB , 2010, CIC.

[29]  Kai-Fu Yang,et al.  Color Constancy Using Double-Opponency , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Jiri Matas,et al.  Revisiting Gray Pixel for Statistical Illumination Estimation , 2019, VISIGRAPP.

[31]  Jonathan T. Barron,et al.  Convolutional Color Constancy , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[32]  Michael S. Brown,et al.  Effective learning-based illuminant estimation using simple features , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Graham D. Finlayson,et al.  Corrected-Moment Illuminant Estimation , 2013, 2013 IEEE International Conference on Computer Vision.

[34]  Sven Loncaric,et al.  Color Dog - Guiding the Global Illumination Estimation to Better Accuracy , 2015, VISAPP.

[35]  E. Land.  The retinex theory of color vision. , 1977, Scientific American.

[36]  G. Buchsbaum.  A spatial processor model for object colour perception , 1980 .

[37]  Sven Loncaric,et al.  Puma: A high-quality retinex-based tone mapping operator , 2016, 2016 24th European Signal Processing Conference (EUSIPCO).

[38]  Peter V. Gehler,et al.  A Curious Problem with Using the Colour Checker Dataset for Illuminant Estimation , 2017, CIC.

[39]  Peter V. Gehler,et al.  Rehabilitating the Color Checker Dataset for Illuminant Estimation , 2018, CIC.

[40]  Ming Zhang,et al.  Improving Color Constancy by Discounting the Variation of Camera Spectral Sensitivity , 2016, Journal of the Optical Society of America. A, Optics, image science, and vision.

[41]  Dilip K Prasad,et al.  Illuminant estimation for color constancy: why spatial-domain methods work and the role of the color distribution. , 2014, Journal of the Optical Society of America. A, Optics, image science, and vision.