Image Restoration using Feature-guidance

TL;DR

This paper introduces a novel two-stage image restoration method that localizes degraded regions and uses auxiliary degradation masks to guide restoration, improving performance on spatially-varying artifacts.

Contribution

It proposes a new approach combining degradation localization with mask-guided restoration using attentive knowledge distillation, addressing spatially-varying degradation challenges.

Findings

Significant improvement over strong baselines.

Effective localization of degraded regions.

Enhanced restoration quality with mask-guided modules.

Abstract

Image restoration is the task of recovering a clean image from a degraded version. In most cases, the degradation is spatially varying, and it requires the restoration network to both localize and restore the affected regions. In this paper, we present a new approach suitable for handling the image-specific and spatially-varying nature of degradation in images affected by practically occurring artifacts such as blur, rain-streaks. We decompose the restoration task into two stages of degradation localization and degraded region-guided restoration, unlike existing methods which directly learn a mapping between the degraded and clean images. Our premise is to use the auxiliary task of degradation mask prediction to guide the restoration process. We demonstrate that the model trained for this auxiliary task contains vital region knowledge, which can be exploited to guide the restoration network's training using attentive knowledge distillation technique. Further, we propose mask-guided convolution and global context aggregation module that focuses solely on restoring the degraded regions. The proposed approach's effectiveness is demonstrated by achieving significant improvement over strong baselines.