Related papers: Analyzing Perception-Distortion Tradeoff using Enh…
Recent research on super-resolution has progressed with the development of deep convolutional neural networks (DCNN). In particular, residual learning techniques exhibit improved performance. In this paper, we develop an enhanced deep…
In this paper, we propose a deep generative adversarial network for super-resolution considering the trade-off between perception and distortion. Based on good performance of a recently developed model for super-resolution, i.e., deep…
High perceptual quality and low distortion degree are two important goals in image restoration tasks such as super-resolution (SR). Most of the existing SR methods aim to achieve these goals by minimizing the corresponding yet conflicting…
Image restoration algorithms are typically evaluated by some distortion measure (e.g. PSNR, SSIM, IFC, VIF) or by human opinion scores that quantify perceived perceptual quality. In this paper, we prove mathematically that distortion and…
Single-image super-resolution (SISR) networks trained with perceptual and adversarial losses provide high-contrast outputs compared to those of networks trained with distortion-oriented losses, such as L1 or L2. However, it has been shown…
The distortion-perception (DP) tradeoff reveals a fundamental conflict between distortion metrics (e.g., MSE and PSNR) and perceptual quality. Recent research has increasingly concentrated on evaluating denoising algorithms within the DP…
Single-image super-resolution (SR) has achieved remarkable progress with deep learning, yet most approaches rely on distortion-oriented losses or heuristic perceptual priors, which often lead to a trade-off between fidelity and visual…
The proposal of perceptual loss solves the problem that per-pixel difference loss function causes the reconstructed image to be overly-smooth, which acquires a significant progress in the field of single image super-resolution…
This paper presents a comprehensive study and benchmark on Efficient Perceptual Super-Resolution (EPSR). While significant progress has been made in efficient PSNR-oriented super resolution, approaches focusing on perceptual quality metrics…
Single image super-resolution (SISR) is an ill-posed problem with an indeterminate number of valid solutions. Solving this problem with neural networks would require access to extensive experience, either presented as a large training set…
In image super-resolution, both pixel-wise accuracy and perceptual fidelity are desirable. However, most deep learning methods only achieve high performance in one aspect due to the perception-distortion trade-off, and works that…
Single image super resolution (SISR) is to reconstruct a high resolution image from a single low resolution image. The SISR task has been a very attractive research topic over the last two decades. In recent years, convolutional neural…
Flow-based generative super-resolution (SR) models learn to produce a diverse set of feasible SR solutions, called the SR space. Diversity of SR solutions increases with the temperature ($\tau$) of latent variables, which introduces random…
We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that…
Signal degradation is ubiquitous and computational restoration of degraded signal has been investigated for many years. Recently, it is reported that the capability of signal restoration is fundamentally limited by the perception-distortion…
Recently, convolutional networks have achieved remarkable development in remote sensing image Super-Resoltuion (SR) by minimizing the regression objectives, e.g., MSE loss. However, despite achieving impressive performance, these methods…
One impressive advantage of convolutional neural networks (CNNs) is their ability to automatically learn feature representation from raw pixels, eliminating the need for hand-designed procedures. However, recent methods for single image…
Compared to CNN-based methods, Transformer-based methods achieve impressive image restoration outcomes due to their abilities to model remote dependencies. However, how to apply Transformer-based methods to the field of blind…
Deep convolutional neural networks (CNNs) have recently achieved great success for single image super-resolution (SISR) task due to their powerful feature representation capabilities. The most recent deep learning based SISR methods focus…
The presence of residual and dense neural networks which greatly promotes the development of image Super-Resolution(SR) have witnessed a lot of impressive results. Depending on our observation, although more layers and connections could…