Beyond the Ground Truth: Enhanced Supervision for Image Restoration

TL;DR

This paper introduces a framework that enhances ground truth images using adaptive frequency masks and super-resolution, providing better supervision for real-world image restoration models.

Contribution

It proposes a novel frequency-domain mixup technique to generate higher-quality supervision images, improving restoration performance without hallucinating artifacts.

Findings

Enhanced ground truth images lead to better restoration quality.

The approach improves perceptual quality while maintaining semantic consistency.

User studies confirm the effectiveness of supervision enhancement.

Abstract

Deep learning-based image restoration has achieved significant success. However, when addressing real-world degradations, model performance is limited by the quality of groundtruth images in datasets due to practical constraints in data acquisition. To address this limitation, we propose a novel framework that enhances existing ground truth images to provide higher-quality supervision for real-world restoration. Our framework generates perceptually enhanced ground truth images using super-resolution by incorporating adaptive frequency masks, which are learned by a conditional frequency mask generator. These masks guide the optimal fusion of frequency components from the original ground truth and its super-resolved variants, yielding enhanced ground truth images. This frequency-domain mixup preserves the semantic consistency of the original content while selectively enriching perceptual details, preventing hallucinated artifacts that could compromise fidelity. The enhanced ground truth images are used to train a lightweight output refinement network that can be seamlessly integrated with existing restoration models. Extensive experiments demonstrate that our approach improves the quality of restored images. We further validate the effectiveness of both supervision enhancement and output refinement through user studies.