paper-with-me

Papers

Super-Resolution using Convolutional Neural Networks without Any Checkerboard Artifacts

2018-06-07 · Yusuke Sugawara, Sayaka Shiota, Hitoshi Kiya

It is well-known that a number of excellent super-resolution (SR) methods using convolutional neural networks (CNNs) generate checkerboard artifacts. A condition to avoid the checkerboard artifacts is proposed in this paper. So far, checkerboard artifacts have been mainly studied for linear multirate systems, but the condition to avoid checkerboard artifacts can not be applied to CNNs due to the non-linearity of CNNs. We extend the avoiding condition for CNNs, and apply the proposed structure to some typical SR methods to confirm the effectiveness of the new scheme. Experiment results demonstrate that the proposed structure can perfectly avoid to generate checkerboard artifacts under two loss conditions: mean square error and perceptual loss, while keeping excellent properties that the SR methods have.

📄 PDF Abstract BibTeX arXiv:1806.02658

Code (1)

r06922019/butt_lion_paper_notes pytorch

Tasks

Super-Resolution

Similar Papers 제목 키워드 기반

Checkerboard-Artifact-Free Image-Enhancement Network Considering Local and Global Features

2020-10-13 · Yuma Kinoshita, Hitoshi Kiya

In this paper, we propose a novel convolutional neural network (CNN) that never causes checkerboard artifacts, for image enhancement. In research fields of image-to-image translation problems, it is well-known that image…

Image EnhancementImage-to-Image TranslationSSIMTranslation

CycleGAN without checkerboard artifacts for counter-forensics of fake-image detection

2020-12-01 · 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. Recent rapid advances in image manipulation tools and deep image synthesis techniques, such as Gene…

Fake Image DetectionImage GenerationImage Manipulation

Fixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs

2020-02-06 · Yuma Kinoshita, Hitoshi Kiya

In this paper, we propose a fixed convolutional layer with an order of smoothness not only for avoiding checkerboard artifacts in convolutional neural networks (CNNs) but also for enhancing the performance of CNNs, where…

General Classificationimage-classificationImage ClassificationImage Generation

Order and Chaos: NTK views on DNN Normalization, Checkerboard and Boundary Artifacts

2019-07-11 · Arthur Jacot, Franck Gabriel, François Ged, Clément Hongler

We analyze architectural features of Deep Neural Networks (DNNs) using the so-called Neural Tangent Kernel (NTK), which describes the training and generalization of DNNs in the infinite-width setting. In this setting, we…

ACE: Artificial Checkerboard Enhancer to Induce and Evade Adversarial Attacks

2019-05-01 · ICLR 2019 5 · Jisung Hwang, Younghoon Kim, Sanghyuk Chun, Jaejun Yoo 외

The checkerboard phenomenon is one of the well-known visual artifacts in the computer vision field. The origins and solutions of checkerboard artifacts in the pixel space have been studied for a long time, but their effe…