Computational Color Constancy: Survey and Experiments

By Arjan Gijsenij, Theo Gevers, Joost van de Weijer. IEEE Transactions on Image Processing, 2011

591 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/2071002b9f3edcbe46daedd1e3576cd1fb0be22f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

1. Tali Treibitz
2. Derya Akkaynak
3. Aitor Alvarez-Gila
4. Shuicheng Yan
5. Dilip K. Prasad
6. Baocai Yin
7. Rynson W. H. Lau
8. Robby T. Tan

In Computer Vision and Pattern Recognition

1. Ming-Hsuan Yang
2. Luc Van Gool
3. Dacheng Tao
4. Jiashi Feng
5. Chen Change Loy
6. Shuicheng Yan
7. Lei Zhang
8. Xiaogang Wang

In Media Technology

1. Wenhan Yang
2. Jiaying Liu
3. Tali Treibitz
4. Derya Akkaynak
5. Jianrui Cai
6. Rynson W. H. Lau
7. Xin Yang
8. Ke Xu

Citations in the corpus

• Learning to Restore Low-Light Images via Decomposition-and-Enhancement (2020, background): “White balance algorithms aim to correct unrealistic casts via estimating the per-channel gain [16].”
• Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis (2017, background): “Usually, the input of skin image understanding techniques undergoes a color normalization step, in order to achieve color constancy [6].”
• Learning Image-Adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-Time (2020, background): “For the enhancement part, those modules include exposure correction [13], [14], color constancy [15], [16], contrast enhancement [17], [18], color manipulation [19], [20] and tone mapping [21], [22], each of which has been widely studied in the past.”
• Joint Rain Detection and Removal from a Single Image with Contextualized Deep Networks (2020, background): “It equals to enforcing color consistency constraint [57], [58], [59], [60] on the networks, which is beneficial for decreasing the color bias of the training data and generating naturally looking results in colors.”
• Sea-Thru: A Method for Removing Water From Underwater Images (2019, methodology): “This can be done using statistical or learning based methods (see [32] for a survey); here for the scenes that contain a sufficiently diverse set of colors, we adopt the simple and fast Gray World Hypothesis [14], and for monochromatic scenes (such as in our dataset D4 we introduce next), we use a s”
• Illuminant estimation for color constancy: why spatial-domain methods work and the role of the color distribution. (2014, methodology): “metric to evaluate the methods as it is most widely used in evaluating color constancy algorithms [9] and is correlated to the perceptual Euclidean distance [45].”
• Color Constancy by Learning to Predict Chromaticity from Luminance (2015, background): “24 End-to-end Trained 2.56 1.67 1.89 0.91 3.30 5.56 (10-Fold) Empirical 2.55 1.58 1.83 0.85 3.30 5.74 End-to-end Trained 2.20 1.37 1.53 0.69 2.68 4.89 *Errors after correcting estimates from [22] for black level offset (see text and supplementary material). Data for all other methods is from [18]. m”