Not All Degradations Are Equal: A Targeted Feature Denoising Framework for Generalizable Image Super-Resolution
This work addresses the challenge of making super-resolution models more robust to unknown degradations, which is important for practical applications, though it builds incrementally on existing regularization methods.
The paper tackles the problem of generalizable image super-resolution by showing that models primarily overfit to noise rather than all degradation types, and proposes a targeted feature denoising framework that achieves superior performance across five benchmarks with both synthetic and real-world data.
Generalizable Image Super-Resolution aims to enhance model generalization capabilities under unknown degradations. To achieve this goal, the models are expected to focus only on image content-related features instead of overfitting degradations. Recently, numerous approaches such as Dropout and Feature Alignment have been proposed to suppress models' natural tendency to overfit degradations and yield promising results. Nevertheless, these works have assumed that models overfit to all degradation types (e.g., blur, noise, JPEG), while through careful investigations in this paper, we discover that models predominantly overfit to noise, largely attributable to its distinct degradation pattern compared to other degradation types. In this paper, we propose a targeted feature denoising framework, comprising noise detection and denoising modules. Our approach presents a general solution that can be seamlessly integrated with existing super-resolution models without requiring architectural modifications. Our framework demonstrates superior performance compared to previous regularization-based methods across five traditional benchmarks and datasets, encompassing both synthetic and real-world scenarios.