Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution
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 successfully balance the trade-off rely on fusing results from separately trained models with ad-hoc post-processing. In this paper, we propose a novel super-resolution model with a low-frequency constraint (LFc-SR), which balances the objective and perceptual quality through a single model and yields super-resolved images with high PSNR and perceptual scores. We further introduce an ADMM-based alternating optimization method for the non-trivial learning of the constrained model. Experiments showed that our method, without cumbersome post-processing procedures, achieved the state-of-the-art performance. The code is available at https://github.com/Yuehan717/PDASR.
Code (1)
Tasks
Image Super-ResolutionSuper-ResolutionSimilar Papers 제목 키워드 기반
Perception-Distortion Balanced Super-Resolution: A Multi-Objective Optimization Perspective
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 correspondi…
Image RestorationSuper-ResolutionOptimized Signal Distortion for PAPR Reduction of OFDM Signals with IFFT/FFT Complexity via ADMM Approaches
In this paper, we propose two low-complexity optimization methods to reduce peak-to-average power ratio (PAPR) values of orthogonal frequency division multiplexing (OFDM) signals via alternating direction method of multi…
On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method
Robust machine learning is currently one of the most prominent topics which could potentially help shaping a future of advanced AI platforms that not only perform well in average cases but also in worst cases or adverse …
Adversarial AttackBayesian Optimizationimage-classificationImage ClassificationPerceptual-Distortion Balanced Image Super-Resolution is a Multi-Objective Optimization Problem
Training Single-Image Super-Resolution (SISR) models using pixel-based regression losses can achieve high distortion metrics scores (e.g., PSNR and SSIM), but often results in blurry images due to insufficient recovery o…
Bayesian OptimizationImage Quality AssessmentImage RestorationImage Super-Resolution+2CAE-ADMM: Implicit Bitrate Optimization via ADMM-based Pruning in Compressive Autoencoders
We introduce ADMM-pruned Compressive AutoEncoder (CAE-ADMM) that uses Alternative Direction Method of Multipliers (ADMM) to optimize the trade-off between distortion and efficiency of lossy image compression. Specificall…
Image CompressionMS-SSIMNeural Architecture SearchSSIM