Efficient Color Constancy with Local Surface Reflectance Statistics

Gao, Shaobing; Han, Wangwang; Yang, Kai-Fu; Li, Chaoyi; Li, Yongjie

doi:10.1007/978-3-319-10605-2_11

Cited by 40 publications

(36 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The simplest such method is Gray World [7] that assumes that the global average of reflectance is achromatic. The generalization of this assumption by restricting it to local patches and higherorder gradients has led to more powerful statistics-based methods, such as White Patch [6], General Gray World [2], Gray Edge [38], Shades-of-Gray [17] and LSRS [19], among others [12].…”

Section: Related Workmentioning

confidence: 99%

On Finding Gray Pixels

Qian

Kämäräinen

Nikkanen³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

We propose a novel grayness index for finding gray pixels and demonstrate its effectiveness and efficiency in illumination estimation. The grayness index, GI in short, is derived using the Dichromatic Reflection Model and is learning-free. GI allows to estimate one or multiple illumination sources in color-biased images. On standard singleillumination and multiple-illumination estimation benchmarks, GI outperforms state-of-the-art statistical methods and many recent deep methods. GI is simple and fast, written in a few dozen lines of code, processing a 1080p image in ∼ 0.4 seconds with a non-optimized Matlab code.

show abstract

Section: Related Workmentioning

confidence: 99%

On Finding Gray Pixels

Qian

Kämäräinen

Nikkanen³

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…As did in many papers, in this work we reasonably assume a single light source color across a scene [3], [7], [30], [31], [32]. Based on the common form of the linear imaging equation, the interaction of surface, light source, and sensor can be indicated by a simple equation written as [3], [4]…”

Section: Constancymentioning

confidence: 99%

“…In general, CC aims at removing the color bias in captured image f c (x) by first estimating the illuminant I c , c ∈ {R, G, B}, then recovering C c (x) by dividing f c (x) by I c . However, both I c and C c (x) in Eq (2) are usually unknown and hence, given only the image values f c (x), estimating I c is a typical ill-posed problem that cannot be solved without further constraints [30], [35], [36], [37], [38]. While many existing algorithms rely on aforementioned steps to achieve CC, it should be explicitly pointed out that these algorithms are camera dependent (e.g., a fixed camera [8]).…”

Section: Constancymentioning

confidence: 99%

“…Alternatively, if we replace the features K(f c (x)) with the illuminant estimated by multiple low-level based CC algorithms [5], [30], [35], [36], [37], [38], the regression problem mentioned above is boiled down to the so-called committed-based CC [47], [48], [49], [50]. In this protocol, L is no longer regarded as a feature mapping matrix but a weighted matrix that tries to 'optimally' fuse the output of multiple CC methods as a single illuminant estimate under certain rule (e.g., the weights are optimized in the least mean square (LMS) sense).…”

Section: A About the Learning-based CCmentioning

confidence: 99%

See 1 more Smart Citation

Improving color constancy by discounting the variation of camera spectral sensitivity

Gao

Zhang

et al. 2017

J. Opt. Soc. Am. A

View full text Add to dashboard Cite

It is an ill-posed problem to recover the true scene colors from a color biased image by discounting the effects of scene illuminant and camera spectral sensitivity (CSS) at the same time. Most color constancy (CC) models have been designed to first estimate the illuminant color, which is then removed from the color biased image to obtain an image taken under white light, without the explicit consideration of CSS effect on CC. This paper first studies the CSS effect on illuminant estimation arising in the inter-dataset-based CC (inter-CC), i.e., training a CC model on one dataset and then testing on another dataset captured by a distinct CSS. We show the clear degradation of existing CC models for inter-CC application. Then a simple way is proposed to overcome such degradation by first learning quickly a transform matrix between the two distinct CSSs (CSS-1 and CSS-2). The learned matrix is then used to convert the data (including the illuminant ground truth and the color-biased images) rendered under CSS-1 into CSS-2, and then train and apply the CC model on the color-biased images under CSS-2 without the need of burdensome acquiring of the training set under CSS-2. Extensive experiments on synthetic and real images show that our method can clearly improve the inter-CC performance for traditional CC algorithms. We suggest that, by taking the CSS effect into account, it is more likely to obtain the truly color constant images invariant to the changes of both illuminant and camera sensors.

show abstract

“…For decades, the classical approaches for color constancy in digital cameras, statistical methods, have relied on the assumption that some global or local statistical properties of the illumination are constant and can therefore be estimated directly from the image (Brainard and Wandell, 1986;Barnard et al, 2002;Van De Weijer et al, 2007;Finlayson and Trezzi, 2004;Gao et al, 2014;Yang et al, 2015;Cheng et al, 2014). This approach has the advantage of being independent to the acquisition device since the properties of the scene illumination are estimated in a per-image basis.…”

Section: Introductionmentioning

confidence: 99%

Revisiting Gray Pixel for Statistical Illumination Estimation

Qian

Pertuz

Nikkanen³

et al. 2019

Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

We present a statistical color constancy method that relies on novel gray pixel detection and mean shift clustering. The method, called Mean Shifted Grey Pixel -MSGP, is based on the observation: true-gray pixels are aligned towards one single direction. Our solution is compact, easy to compute and requires no training. Experiments on two real-world benchmarks show that the proposed approach outperforms state-of-the-art methods in the camera-agnostic scenario. In the setting where the camera is known, MSGP outperforms all statistical methods. 1 We assume the image is with linear response and calibrated black offset, where color constancy method should be applied. Note that images over web are not usually this case.

show abstract

Efficient Color Constancy with Local Surface Reflectance Statistics

Cited by 40 publications

References 33 publications

On Finding Gray Pixels

On Finding Gray Pixels

Improving color constancy by discounting the variation of camera spectral sensitivity

Revisiting Gray Pixel for Statistical Illumination Estimation

Contact Info

Product

Resources

About