Bayesian color constancy revisited

By Peter Gehler, Carsten Rother, Andrew Blake, Tom Minka, Toby Sharp. 2008 IEEE Conference on Computer Vision and Pattern Recognition, 2008

457 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/43286039b84c97343a0318edc88307abf60be388

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. Sylvain Paris
2. Frédo Durand
3. Eric Chan
4. Ling Shao
5. Wenqi Ren
6. Dilip K. Prasad
7. Ming-Hsuan Yang
8. Xiaochun Cao

In Computer Vision and Pattern Recognition

1. Ming-Hsuan Yang
2. Ling Shao
3. Luc Van Gool
4. Dacheng Tao
5. Jitendra Malik
6. Xiaogang Wang
7. Trevor Darrell
8. Alan L. Yuille

In Media Technology

1. Ming-Hsuan Yang
2. Wenqi Ren
3. Xiaochun Cao
4. Ayan Chakrabarti
5. Xiangyu Xu
6. Dongwei Ren
7. Ling Shao
8. Lin Ma

Citations in the corpus

• Low-Light Image Enhancement via a Deep Hybrid Network (2019, background): “Since estimating the clear image R(x) and the illumination L(x) from a single observed image is an ill-posed inverse problem, numerous low-light image enhancement methods have been proposed [5]–[8] in recent years.”
• Illuminant estimation for color constancy: why spatial-domain methods work and the role of the color distribution. (2014, methodology): “This figure shows some examples from the Color Checker dataset [40] in which the error in illumination estimation is high when only bright pixels (B) are used and reduces significantly when both bright and dark (BD) pixels are used.”
• Computational Color Constancy: Survey and Experiments (2011, unknown): “[102] introduced a database, consisting of 568 images, both indoor and outdoor.”
• STAR: A Structure and Texture Aware Retinex Model (2019, methodology): “93 Method Bayesian [57] CNNs [58] Gray-World [54] MAE↓ 4.”
• Color Constancy by Learning to Predict Chromaticity from Luminance (2015, methodology): “Table 1 compares the performance of illuminant estimation with our method (see rows labeled “Empirical”) to the current state-of-the-art, using different quantiles of angular error across the Gehler-Shi database [14, 15].”
• Learning photographic global tonal adjustment with a database of input/output image pairs (2011, background): “[7] have shown that supervised learning can be a successful approach to inferring the color of the light that illuminates a scene.”
• Color Invariants for Person Reidentification (2013, unknown): “[20].”