让自监督超分模型更关注高分辨率图像，生成更自然结果
High-Resolution Be Aware! Improving the Self-Supervised Real-World Super-Resolution
- 通过控制器动态调整退化建模，提升对真实退化的感知
- 引入特征对齐正则项，直接约束超分图像分布
- 可适配现有超分模型，适用于真实场景图像增强
自监督学习对真实世界超分至关重要，因真实场景中缺乏真值图像。现有方法依赖低分辨率图像构建伪配对或强制低分辨率重建目标，但难以建模真实退化过程，且缺乏对高分辨率图像的知识，导致生成结果不自然。本文通过增强对高分辨率图像的感知能力，改进自监督真实世界超分。提出一个控制器，根据超分结果质量动态调整退化建模；引入一种新型特征对齐正则项，直接约束超分图像的分布。该方法可微调现成的超分模型以适应特定真实域。实验表明，其生成的图像自然度高，在感知性能上达到当前最优水平。
原文摘要 · Abstract (English)
Self-supervised learning is crucial for super-resolution because ground-truth images are usually unavailable for real-world settings. Existing methods derive self-supervision from low-resolution images by creating pseudo-pairs or by enforcing a low-resolution reconstruction objective. These methods struggle with insufficient modeling of real-world degradations and the lack of knowledge about high-resolution imagery, resulting in unnatural super-resolved results. This paper strengthens awareness of the high-resolution image to improve the self-supervised real-world super-resolution. We propose a controller to adjust the degradation modeling based on the quality of super-resolution results. We also introduce a novel feature-alignment regularizer that directly constrains the distribution of super-resolved images. Our method finetunes the off-the-shelf SR models for a target real-world domain. Experiments show that it produces natural super-resolved images with state-of-the-art perceptual performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。