Enhancing image restoration through learning context-rich and detail-accurate features

Abstract

Image restoration aims to recover high-quality images from their degraded counterparts, necessitating a delicate balance between preserving spatial details and capturing contextual information. Although some methods attempt to address this trade-off, they tend to focus primarily on spatial features while overlooking the importance of understanding frequency variations. Moreover, these approaches commonly utilize skip connections–implemented via addition or concatenation–to fuse encoder and decoder features for improved restoration. However, since encoder features may still carry degradation artifacts, such direct fusion strategies risk introducing implicit noise, ultimately hindering restoration performance. In this paper, we present a multi-scale design that optimally balances these competing objectives, seamlessly integrating spatial and frequency domain knowledge to selectively recover the most informative information. Specifically, we develop a hybrid scale frequency selection block (HSFSBlock), which not only captures multi-scale information from the spatial domain, but also selects the most informative components for image restoration in the frequency domain. Furthermore, to mitigate the inherent noise introduced by skip connections employing only addition or concatenation, we introduce a skip connection attention mechanism (SCAM) to selectively determines the information that should propagate through skip connections. The resulting tightly interlinked architecture, named as LCDNet. Extensive experiments conducted across diverse image restoration tasks showcase that our model attains performance levels that are either superior or comparable to those of state-of-the-art algorithms. The code and the pre-trained models are released at https://github.com/Tombs98/LCDNet.