no code implementations • 3 Aug 2022 • Teruaki Akazawa, Yuma Kinoshita, Hitoshi Kiya
In this paper, we propose a novel template matching method with a white balancing adjustment, called N-white balancing, which was proposed for multi-illuminant scenes.
no code implementations • 12 Jul 2022 • Hitoshi Kiya, Ryota Iijima, MaungMaung AprilPyone, Yuma Kinoshita
In this paper, we propose a combined use of transformed images and vision transformer (ViT) models transformed with a secret key.
no code implementations • 24 May 2022 • Zheng Qi, AprilPyone MaungMaung, Yuma Kinoshita, Hitoshi Kiya
In this paper, we propose a privacy-preserving image classification method that is based on the combined use of encrypted images and the vision transformer (ViT).
no code implementations • 26 Jan 2022 • Hitoshi Kiya, AprilPyone MaungMaung, Yuma Kinoshita, Shoko Imaizumi, Sayaka Shiota
In this paper, we focus on a class of image transformation referred to as learnable image encryption, which is applicable to privacy-preserving machine learning and adversarially robust defense.
no code implementations • 5 Nov 2021 • Yuma Kinoshita, Hitoshi Kiya
Intrinsic image decomposition aims to decompose an image into illumination-invariant and illumination-variant components, referred to as ``reflectance'' and ``shading,'' respectively.
no code implementations • 3 Sep 2021 • Teruaki Akazawa, Yuma Kinoshita, Hitoshi Kiya
In this paper, we propose a novel white balance adjustment, called "spatially varying white balancing," for single, mixed, and non-uniform illuminants.
no code implementations • 1 Jun 2021 • Yuma Kinoshita, Hitoshi Kiya
In this paper, we propose a novel method for separately estimating spectral distributions from images captured by a typical RGB camera.
no code implementations • 21 May 2021 • Teruaki Akazawa, Yuma Kinoshita, Hitoshi Kiya
In this paper, we propose a novel multi-color balance adjustment for color constancy.
no code implementations • 1 Dec 2020 • Takayuki Osakabe, Miki Tanaka, Yuma Kinoshita, Hitoshi Kiya
In this paper, we propose a novel CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection.
no code implementations • 13 Oct 2020 • Yuma Kinoshita, Hitoshi Kiya
In this paper, we propose a novel convolutional neural network (CNN) that never causes checkerboard artifacts, for image enhancement.
no code implementations • 7 Aug 2020 • Hiroki Ito, Yuma Kinoshita, Hitoshi Kiya
We propose a transformation network for generating visually-protected images for privacy-preserving DNNs.
no code implementations • 6 Feb 2020 • Yuma Kinoshita, Hitoshi Kiya
In an image-classification experiment with four CNNs: a simple CNN, VGG8, ResNet-18, and ResNet-101, applying the fixed layers to these CNNs is shown to improve the classification performance of all CNNs.
no code implementations • 1 Nov 2019 • Ayana Kawamura, Yuma Kinoshita, Hitoshi Kiya
In this paper, we propose a novel privacy-preserving machine learning scheme with encrypted images, called EtC (Encryption-then-Compression) images.
no code implementations • 22 Aug 2019 • Chihiro Go, Yuma Kinoshita, Sayaka Shiota, Hitoshi Kiya
This paper proposes a novel multi-exposure image fusion (MEF) scheme for single-shot high dynamic range imaging with spatially varying exposures (SVE).
no code implementations • 1 Aug 2019 • Chihiro Go, Yuma Kinoshita, Sayaka Shiota, Hitoshi Kiya
We proposes a novel single-shot high dynamic range imaging scheme with spatially varying exposures (SVE) considering hue distortion.
no code implementations • 7 May 2019 • Yuma Kinoshita, Hitoshi Kiya
To handle both local and global features, the proposed architecture consists of three networks: a local encoder, a global encoder, and a decoder.
no code implementations • 24 Apr 2019 • Chien-Cheng Chien, Yuma Kinoshita, Hitoshi Kiya
These methods, however, have two problems: (1) The loss of details in bright regions due to over-enhancement of contrast.
Multimedia
no code implementations • 17 Jan 2019 • Yuma Kinoshita, Hitoshi Kiya
Most of conventional image enhancement methods, including Retinex based methods, do not take into account restoring lost pixel values caused by clipping and quantizing.
no code implementations • 8 Nov 2018 • Chien Cheng Chien, Yuma Kinoshita, Sayaka Shiota, Hitoshi Kiya
This paper proposes a novel image contrast enhancement method based on both a noise aware shadow-up function and Retinex (retina and cortex) decomposition.
no code implementations • 1 Aug 2018 • Yuma Kinoshita, Sayaka Shiota, Hitoshi Kiya
The proposed method enables us to produce pseudo multi-exposure images from a single image.
no code implementations • 23 Jun 2018 • Yuma Kinoshita, Taichi Yoshida, Sayaka Shiota, Hitoshi Kiya
This paper proposes a novel multi-exposure image fusion method based on exposure compensation.
no code implementations • 29 May 2018 • Yuma Kinoshita, Sayaka Shiota, Hitoshi Kiya
In conventional works, it has been pointed out that the quality of those multi-exposure images can be improved by adjusting the luminance of them.