White Balancing by Using Multiple Images via Intrinsic Image Decomposition

Matsuoka, Ryota; Baba, Tatsuya; Rizkinia, Mia; Okuda, Masahiro

doi:10.1587/transinf.2015edp7070

Cited by 9 publications

(8 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, let D v and D h ∈ R N×N be the vertical and horizontal first-order differential operators with a Neumann boundary, respectively; the differential operator is then defined by D 1 := [D v D h ] (∈ R 2N×N ) for a gray image and D := diag(D 1 , D 1 , D 1 )(∈ R 6N×3N ) for a color image. In the 0 gradient minimization, the group sparsity of the RGB gradients is considered by concatenating the 1 -norm [31,37,48], and it is defined as…”

Section: Gradientmentioning

confidence: 99%

“…The popular total variation (TV) [1] is designed as the total magnitude of the vertical and horizontal discrete gradients of an image and promotes this smoothness property on optimization. This method can be employed in more advanced image restoration problems, e.g., reflection removal [42,43], rain streak removal [44][45][46], intrinsic image decomposition [36,47,48], image blending [49], and multispectral pansharpening [50][51][52][53], which are complex problems to solve using filtering-based techniques; this is because optimization-based methods can explicitly and quantitatively design observation models by modeling using some norms and specific functions approximately. For example, we can flexibly define not only the commonly used 2 -norm but also the 1 -norm [54,55] and Huber loss function [49,56,57], which are robust to outliers, and so on, as a data-fidelity term in minimization problems.…”

Section: Introductionmentioning

confidence: 99%

“…In this method, the 0 gradient, which is the number of nonzero gradients of an image, is minimized together with the 2 data fidelity to an input image. Recently, the applications of this method were actively studied, such as algorithm acceleration [58], deblurring [3,4], multi-dimensional data smoothing [58], and layer separation [48,59]. Ono investigated the 0 gradient projection in [37], which allows us to control the degree of smoothing of the output image intuitively.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Beyond Staircasing Effect: Robust Image Smoothing via ℓ0 Gradient Minimization and Novel Gradient Constraints

Matsuoka,

Okuda

2023

Signals

Self Cite

View full text Add to dashboard Cite

In this paper, we propose robust image-smoothing methods based on ℓ0 gradient minimization with novel gradient constraints to effectively suppress pseudo-edges. Simultaneously minimizing the ℓ0 gradient, i.e., the number of nonzero gradients in an image, and the ℓ2 data fidelity results in a smooth image. However, this optimization often leads to undesirable artifacts, such as pseudo-edges, known as the “staircasing effect”, and halos, which become more visible in image enhancement tasks, like detail enhancement and tone mapping. To address these issues, we introduce two types of gradient constraints: box and ball. These constraints are applied using a reference image (e.g., the input image is used as a reference for image smoothing) to suppress pseudo-edges in homogeneous regions and the blurring effect around strong edges. We also present an ℓ0 gradient minimization problem based on the box-/ball-type gradient constraints using an alternating direction method of multipliers (ADMM). Experimental results on important applications of ℓ0 gradient minimization demonstrate the advantages of our proposed methods compared to existing ℓ0 gradient-based approaches.

show abstract

Section: Gradientmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Beyond Staircasing Effect: Robust Image Smoothing via ℓ0 Gradient Minimization and Novel Gradient Constraints

Matsuoka,

Okuda

2023

Signals

Self Cite

View full text Add to dashboard Cite

show abstract

“…from the room's artificial tungsten light bulbs). Prior work has formulated a local gray-world assumption to generalize white balance to the mixed-lighting case [11], exploiting the difference in light colors in shadowed vs. sunlit areas for outdoor scenes [25], or flash/no-flash image pairs [33,21,23].…”

Section: Mixed-illumination White-balancementioning

confidence: 99%

A Dataset of Multi-Illumination Images in the Wild

Murmann¹,

Gharbi

Aittala³

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

input ours GT Figure 1. Using our multi-illumination image dataset of over 1000 scenes, we can train neural networks to solve challenging vision tasks. For instance, one of our models can relight an input image to a novel light direction. Specular highlights pose a significant challenge for many relighting algorithms, but are handled gracefully by our network. Further analysis is presented in Section 4.2. AbstractCollections of images under a single, uncontrolled illumination [42] have enabled the rapid advancement of core computer vision tasks like classification, detection, and segmentation [26,43,18]. But even with modern learning techniques, many inverse problems involving lighting and material understanding remain too severely ill-posed to be solved with single-illumination datasets. The data simply does not contain the necessary supervisory signals. Multiillumination datasets are notoriously hard to capture, so the data is typically collected at small scale, in controlled environments, either using multiple light sources [10,53], or robotic gantries [8,20]. This leads to image collections that are not representative of the variety and complexity of real-world scenes. We introduce a new multi-illumination dataset of more than 1000 real scenes, each captured in high dynamic range and high resolution, under 25 lighting conditions. We demonstrate the richness of this dataset by training state-of-the-art models for three challenging applications: single-image illumination estimation, image relighting, and mixed-illuminant white balance.

show abstract

“…In the image processing literature, many methods for the reflectance estimation have been proposed [7]- [21]. Barrow and Tenenbaum [13] introduced a method of intrinsic image decomposition, which separates reflectance and shading components.…”

Section: Introductionmentioning

confidence: 99%

Computationally Efficient Reflectance Estimation for Hyperspectral Images

Okabe

Okuda

2017

IEICE Trans. Inf. & Syst.

Self Cite

View full text Add to dashboard Cite

The Retinex theory assumes that large intensity changes correspond to reflectance edges, while smoothly-varying regions are due to shading. Some algorithms based on the theory adopt simple thresholding schemes and achieve adequate results for reflectance estimation. In this paper, we present a practical reflectance estimation technique for hyperspectral images. Our method is realized simply by thresholding singular values of a matrix calculated from scaled pixel values. In the method, we estimate the reflectance image by measuring spectral similarity between two adjacent pixels. We demonstrate that our thresholding scheme effectively estimates the reflectance and outperforms the Retinex-based thresholding. In particular, our methods can precisely distinguish edges caused by reflectance change and shadows.

show abstract

White Balancing by Using Multiple Images via Intrinsic Image Decomposition

Cited by 9 publications

References 28 publications

Beyond Staircasing Effect: Robust Image Smoothing via ℓ0 Gradient Minimization and Novel Gradient Constraints

Beyond Staircasing Effect: Robust Image Smoothing via ℓ0 Gradient Minimization and Novel Gradient Constraints

A Dataset of Multi-Illumination Images in the Wild

Computationally Efficient Reflectance Estimation for Hyperspectral Images

Contact Info

Product

Resources

About