Super-Resolution using Convolutional Neural Networks without Any Checkerboard Artifacts
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.
Code (1)
Tasks
Super-ResolutionSimilar Papers 제목 키워드 기반
Checkerboard-Artifact-Free Image-Enhancement Network Considering Local and Global Features
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 TranslationSSIMTranslationCycleGAN without checkerboard artifacts for counter-forensics of fake-image detection
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 ManipulationFixed smooth convolutional layer for avoiding checkerboard artifacts in CNNs
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 GenerationOrder and Chaos: NTK views on DNN Normalization, Checkerboard and Boundary Artifacts
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
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…