Siamese dense network for reflection removal with flash and no-flash image pairs

Y Chang, C Jung, J Sun, F Wang - International Journal of Computer …, 2020 - Springer
This work addresses the reflection removal with flash and no-flash image pairs to separate
reflection from transmission. When objects are covered by glass, the no-flash image usually …

Transformed-domain robust multiple-exposure blending with huber loss

R Matsuoka, S Ono, M Okuda - IEEE Access, 2019 - ieeexplore.ieee.org
Pixel-domain weighting methods for multiple-exposure blending can efficiently remove
noise and under-/over-exposed pixels simultaneously in high dynamic range (HDR) image …

Flash/no-flash image integration using convex optimization

T Baba, R Matsuoka, S Ono, K Shirai… - … on Acoustics, Speech …, 2014 - ieeexplore.ieee.org
When high ISO sensitivity is used to acquire images of dark scenes, their detail textures are
often deteriorated by sensor noise. On the other hand, using flash photography with artificial …

Deep gradual flash fusion for low-light enhancement

JW Kim, JH Ryu, JO Kim - Journal of Visual Communication and Image …, 2020 - Elsevier
In this paper, we propose gradual flash fusion, a new imaging concept that enables
acquisition of pseudo multi-exposure images in a passive manner. This means that our …

High dynamic range image acquisition using flash image

R Matsuoka, T Baba, M Okuda… - 2013 IEEE International …, 2013 - ieeexplore.ieee.org
We propose a denoising technique using multiple exposure image integration. When
acquiring a dark scene, the detail of the dark area is often deteriorated by sensor noise. For …

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

R Matsuoka, K Shirai, M Okuda - Signal Processing: Image Communication, 2019 - Elsevier
We propose a reference-based filtering method that transforms the local color distribution of
individual image patches. With our method, the color of a reference image is transformed by …

Misaligned image integration with local linear model

T Baba, R Matsuoka, K Shirai… - IEEE Transactions on …, 2016 - ieeexplore.ieee.org
We present a new image integration technique for a flash and long-exposure image pair to
capture a dark scene without incurring blurring or noisy artifacts. Most existing methods …

Local covariance filtering for color images

K Shirai, M Okuda, T Jinno, M Okamoto… - Computer Vision–ACCV …, 2013 - Springer
In this paper, we introduce a novel edge-aware filter that manipulates the local covariances
of a color image. A covariance matrix obtained at each pixel is decomposed by the singular …

Weight optimization for multiple image integration

R Matsuoka, T Yamauchi, T Baba… - 2013 IEEE International …, 2013 - ieeexplore.ieee.org
We propose a denoising technique using multiple image integration. When acquiring a dark
scene, the detail of the dark area is often deteriorated by sensor noise. A simple image …

Weight optimization for multiple image integration and its applications

R Matsuoka, T Yamauchi, T Baba… - … on Information and …, 2016 - search.ieice.org
We propose an image restoration technique that uses multiple image integration. The detail
of the dark area when acquiring a dark scene is often deteriorated by sensor noise. Simple …