Unsupervised Learning for Color Constancy

Banić, Nikola; Koščević, Karlo; Lončarić, Sven

doi:10.48550/arxiv.1712.00436

Cited by 23 publications

(55 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 1 shows the results of our AWB method on the single-illuminant Cube+ dataset [11]. In this table, we also show the results of a set of ablation studies conducted to show the impact of some training options.…”

Section: Resultsmentioning

confidence: 99%

“…As a part of this effort, we propose a synthetic test set of mixed-illuminant scenes with pixel-wise ground truth. We use this set, along with other datasets ( [11,24]), to validate our method through an extensive set of experiments and comparisons.…”

Section: Contributionmentioning

confidence: 99%

“…Cube+ dataset [11] As the Cube+ dataset [11] is commonly used by prior color constancy work, we used the linear raw images provided in the Cube+ dataset to evaluate our AWB method for single-illuminant scenes. Specifically, we used the raw images in order to generate the small images to feed them into our DNN.…”

Section: Evaluation Setsmentioning

confidence: 99%

See 2 more Smart Citations

Auto White-Balance Correction for Mixed-Illuminant Scenes

Afifi¹,

Brubaker²,

Brown³

2021

Preprint

View full text Add to dashboard Cite

Auto white balance (AWB) is applied by camera hardware at capture time to remove the color cast caused by the scene illumination. The vast majority of white-balance algorithms assume a single light source illuminates the scene; however, real scenes often have mixed lighting conditions. This paper presents an effective AWB method to deal with such mixed-illuminant scenes. A unique departure from conventional AWB, our method does not require illuminant estimation, as is the case in traditional camera AWB modules. Instead, our method proposes to render the captured scene with a small set of predefined white-balance settings. Given this set of rendered images, our method learns to estimate weighting maps that are used to blend the rendered images to generate the final corrected image. Through extensive experiments, we show this proposed method produces promising results compared to other alternatives for single-and mixed-illuminant scene color correction. Our source code and trained models are available at https://github.com/mahmoudnafifi/mixedillWB.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Contributionmentioning

confidence: 99%

See 1 more Smart Citation

Auto White-Balance Correction for Mixed-Illuminant Scenes

Afifi¹,

Brubaker²,

Brown³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In Table 1, we provide the results for the following unsupervised approaches: White-Patch [37], Grey-World [6], Color-PCA [38], Shades-of-Grey [39], Weighted Grey-Edge [8], Greyness Index 2019 [3], Color Tiger [5], PCC Q2 Fig. 2.…”

Section: Experiments On Channel-wise Color Constancymentioning

confidence: 99%

“…The central objective is to recover the true colors of the objects observed as if the light source is a neutral illumination. This task in modern cameras is known as the computational color constancy and several unsupervised [2], [3], [4], [5], [6], [7], [8] and supervised approaches [9], [10], [11], [12], [13], [14], [15], [16] have been proposed to solve it. Achieving an invariant representation of the objects regardless of the illuminant is critical for many other vision tasks such as classification [17], [18] and scene understanding [19], [20], [20], [21].…”

Section: Introductionmentioning

confidence: 99%

Robust channel-wise illumination estimation

Laakom¹,

Raitoharju²,

Nikkanen³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recently, Convolutional Neural Networks (CNNs) have been widely used to solve the illuminant estimation problem and have often led to state-of-the-art results. Standard approaches operate directly on the input image. In this paper, we argue that this problem can be decomposed into three channel-wise independent and symmetric sub-problems and propose a novel CNN-based illumination estimation approach based on this decomposition. The proposed method substantially reduces the number of parameters needed to solve the task while achieving competitive experimental results compared to state-of-the-art methods. Furthermore, the practical application of illumination estimation techniques typically requires identifying the extreme error cases. This can be achieved using an uncertainty estimation technique. In this work, we propose a novel color constancy uncertainty estimation approach that augments the trained model with an auxiliary branch which learns to predict the error based on the feature representation. Intuitively, the model learns which feature combinations are robust and are thus likely to yield low errors and which combinations result in erroneous estimates. We test this approach on the proposed method and show that it can indeed be used to avoid several extreme error cases and, thus, improves the practicality of the proposed technique.

show abstract

Two-stage deep learning framework for sRGB image white balance

Farghaly

Mansour

Sewisy

2022

SIViP

View full text Add to dashboard Cite

This work aims to correct white-balance errors in sRGB images. These white-balance errors are hard to fix due to the nonlinear color-processing procedures applied by camera image signal processors (ISP) to produce the final sRGB colors. Camera ISPs apply these nonlinear procedures after the essential white-balance step to render sensor raw images to the sRGB space through a camera-specific set of tone curves and look-up tables. To correct improperly white-balanced images, projecting non-linear sRGB colors back to their original raw space is required. Recent work formulates the problem as an image translation problem, where input sRGB colors are mapped using nonlinear polynomial correction functions to fix such white-balance errors. In this work, we show that correcting white-balance errors in sRGB images through a global color mapping followed by spatially local adjustments, learned in an end-to-end training, introduces perceptual improvements in the final results. Qualitative and quantitative comparisons with recently published methods for camera-rendered image white balancing validate our method’s efficacy and show that our method achieves competitive results with state-of-the-art methods.

show abstract

Unsupervised Learning for Color Constancy

Cited by 23 publications

References 0 publications

Auto White-Balance Correction for Mixed-Illuminant Scenes

Auto White-Balance Correction for Mixed-Illuminant Scenes

Robust channel-wise illumination estimation

Two-stage deep learning framework for sRGB image white balance

Contact Info

Product

Resources

About