Reference-based local color distribution transformation method and its application to image integration

Matsuoka, Ryota; Shirai, Kohji; Okuda, Masahiro

doi:10.1016/j.image.2019.04.020

Cited by 3 publications

(4 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simply taking the mean of multiple images can help to reduce the amount of random noise. Several authors have investigated more effective exposure-blending methods based on pixel-domain weighting [4]- [10], [12], [14]. To avoid blur and ghost artifacts, the use of burst images taken with a short-exposure and a high ISO setting is an effective approach [7]- [10].…”

Section: B Related Workmentioning

confidence: 99%

“…In the case of {α, δ} = {0.8, ∞}, Gaussian noise is well removed, but outliers usually remain. This is because the Huber loss function set to δ = ∞ is equivalent to the 2 data fidelity from (14), and thus it is sensitive to such non-Gaussian noise. In contrast, in the case of {α, δ} = {0.8, 0.8}, because δ was set so that the balance between Gaussian and non-Gaussian noise removal was appropriate, each noise could be effectively removed simultaneously.…”

Section: Parameter Setting Complexitymentioning

confidence: 99%

“…The objective of high dynamic range (HDR) imaging is to represent the amount of light in a scene with a broad dynamic range, and it is applied to various fields such as computer graphics, medical imaging, in-vehicle cameras, and surveillance systems. Multiple-exposure blending is the most standard approach for HDR imaging because it can easily generate HDR images by blending a set of multiple-exposure images captured with a consumer camera [1]- [14].…”

Section: Introduction a Backgroundmentioning

confidence: 99%

See 2 more Smart Citations

Transformed-Domain Robust Multiple-Exposure Blending With Huber Loss

2019

Self Cite

View full text Add to dashboard Cite

Pixel-domain weighting methods for multiple-exposure blending can efficiently remove noise and under-/over-exposed pixels simultaneously in high dynamic range (HDR) image generation. Various types of noise such as non-Gaussian noise, e.g., Poisson, impulse noise, and pixel saturation, are often superimposed to multiple-exposure images taken with a high ISO setting in a low-light condition. Because almost all existing methods assume Gaussian noise, these methods cannot sufficiently reduce these types of noise. To achieve high-quality HDR image generation in such difficult conditions, we propose a novel multiple-exposure blending method in which image blending is performed in a wavelet domain so as to enhance the denoising performance. In addition, the Huber loss function is utilized as a fidelity measure in blending to make the method robust against outliers. We also introduce an efficient algorithm based on a primal-dual splitting method for solving our optimization problem. The experimental results demonstrate the advantages of the proposed method over several conventional methods. INDEX TERMS Exposure blending, wavelet transform, convex optimization, total variation, primal-dual splitting.

show abstract

Section: B Related Workmentioning

confidence: 99%

Section: Parameter Setting Complexitymentioning

confidence: 99%

Section: Introduction a Backgroundmentioning

confidence: 99%

See 1 more Smart Citation

Transformed-Domain Robust Multiple-Exposure Blending With Huber Loss

2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Filtering-based smoothing methods, e.g., a bilateral filter [6,21], a guided filter [22][23][24][25], and a nonlocal mean filter [26,27], have been actively studied for a long time and are often used in practical situations, as they can easily obtain smooth images that roughly maintain the structural gradients of input images with a relatively low computational cost.…”

Section: Introductionmentioning

confidence: 99%

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

Reflection Removal Using Multiple Polarized Images with Different Exposure Times

Aizu

Matsuoka

2022

2022 30th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Reference-based local color distribution transformation method and its application to image integration

Cited by 3 publications

References 50 publications

Transformed-Domain Robust Multiple-Exposure Blending With Huber Loss

Transformed-Domain Robust Multiple-Exposure Blending With Huber Loss

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

Reflection Removal Using Multiple Polarized Images with Different Exposure Times

Contact Info

Product

Resources

About