Dual-Path Coupled Image Deraining Network via Spatial-Frequency Interaction
This work provides an incremental improvement for computer vision applications by enhancing image deraining through better frequency capture.
The paper tackles the problem of image deraining by addressing the neglect of frequency information in existing transformer-based methods, resulting in a new network that outperforms state-of-the-art methods on six benchmarks and improves robustness in downstream vision tasks.
Transformers have recently emerged as a significant force in the field of image deraining. Existing image deraining methods utilize extensive research on self-attention. Though showcasing impressive results, they tend to neglect critical frequency information, as self-attention is generally less adept at capturing high-frequency details. To overcome this shortcoming, we have developed an innovative Dual-Path Coupled Deraining Network (DPCNet) that integrates information from both spatial and frequency domains through Spatial Feature Extraction Block (SFEBlock) and Frequency Feature Extraction Block (FFEBlock). We have further introduced an effective Adaptive Fusion Module (AFM) for the dual-path feature aggregation. Extensive experiments on six public deraining benchmarks and downstream vision tasks have demonstrated that our proposed method not only outperforms the existing state-of-the-art deraining method but also achieves visually pleasuring results with excellent robustness on downstream vision tasks.