Cross-domain attention-guided domain adaptive method for image real rain removal

Existing image deraining methods often rely on synthetic data, but the domain gap between synthetic and real data causes significant performance degradation in real-world scenarios. To address this issue, we propose a Cross-Domain Attention-Guided domain adaptive deraining network (CDAG-network) that learns rainfall characteristics from both synthetic and real data to achieve better generalizability. Firstly, we introduce cross-attention as a fine-grained domain adaptation constraint into the CDAG-network, to enhance its capability in analyzing features from real and synthetic domains and aligning their distributions. Secondly, in light of the complex nature of rain artifacts, we propose the Mixed-Scale Convolutional Transformer (MSCT) block that effectively captures features from both global and local perspectives and improves the spatial perception of the model. With the two key designs, the CDAG-network demonstrates enhanced efficiency in domain adaptation and degradation modeling. Furthermore, we present a novel model for synthesizing rain images, which more accurately emulates rain effects in real-world scenes. Based on this model, we synthesize 9K synthetic rain images that along with 6K real rain images collected from real scenes constitute a new domain adaptive deraining dataset. Extensive experimental results demonstrate that our approach outperforms recent state-of-the-art methods in real-world rain removal task. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.