BriefGPT.xyz
Mar, 2024
图像超分辨率中利用自监督约束
Exploiting Self-Supervised Constraints in Image Super-Resolution
HTML
PDF
Gang Wu, Junjun Jiang, Kui Jiang, Xianming Liu
TL;DR
本篇论文介绍了一种新的自我监督约束方法，称为SSC-SR，用于单幅图像超分辨率处理。该方法采用双向不对称模式和指数移动平均更新目标模型以增强稳定性，能够插入已有的超分辨率模型并在多个基准数据集上实现显著的性能提升。
Abstract
Recent advances in
self-supervised learning
, predominantly studied in high-level visual tasks, have been explored in low-level image processing. This paper introduces a novel self-supervised constraint for
single image
→