A^2Net: Adjacent Aggregation Networks for Image Raindrop Removal
This addresses image quality degradation from raindrops for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of removing raindrops from single images by proposing A^2Net, which uses adjacent aggregation architecture and YUV color space transformation to achieve state-of-the-art performance with significantly reduced parameters.
Existing methods for single images raindrop removal either have poor robustness or suffer from parameter burdens. In this paper, we propose a new Adjacent Aggregation Network (A^2Net) with lightweight architectures to remove raindrops from single images. Instead of directly cascading convolutional layers, we design an adjacent aggregation architecture to better fuse features for rich representations generation, which can lead to high quality images reconstruction. To further simplify the learning process, we utilize a problem-specific knowledge to force the network focus on the luminance channel in the YUV color space instead of all RGB channels. By combining adjacent aggregating operation with color space transformation, the proposed A^2Net can achieve state-of-the-art performances on raindrop removal with significant parameters reduction.