Latent Degradation Representation Constraint for Single Image Deraining

TL;DR

This paper introduces LDRCNet, a novel single image deraining method that explicitly constrains degradation representation learning using a direction-aware encoder and multi-scale interaction, achieving state-of-the-art results.

Contribution

The paper proposes a new network with explicit degradation representation constraints and multi-scale fusion for improved deraining performance.

Findings

Achieves state-of-the-art deraining results on synthetic and real datasets.

Effectively decouples rain streak directionality for better removal.

Improves image detail reconstruction after deraining.

Abstract

Since rain streaks show a variety of shapes and directions, learning the degradation representation is extremely challenging for single image deraining. Existing methods are mainly targeted at designing complicated modules to implicitly learn latent degradation representation from coupled rainy images. This way, it is hard to decouple the content-independent degradation representation due to the lack of explicit constraint, resulting in over- or under-enhancement problems. To tackle this issue, we propose a novel Latent Degradation Representation Constraint Network (LDRCNet) that consists of Direction-Aware Encoder (DAEncoder), UNet Deraining Network, and Multi-Scale Interaction Block (MSIBlock). Specifically, the DAEncoder is proposed to adaptively extract latent degradation representation by using the deformable convolutions to exploit the direction consistency of rain streaks. Next, a constraint loss is introduced to explicitly constraint the degradation representation learning during training. Last, we propose an MSIBlock to fuse with the learned degradation representation and decoder features of the deraining network for adaptive information interaction, which enables the deraining network to remove various complicated rainy patterns and reconstruct image details. Experimental results on synthetic and real datasets demonstrate that our method achieves new state-of-the-art performance.