DDT: Dual-branch Deformable Transformer for Image Denoising
This work addresses efficiency issues in image denoising for computer vision applications, representing an incremental improvement by optimizing transformer-based methods.
The paper tackles the challenge of high computational complexity in applying transformers to image denoising by proposing a Dual-branch Deformable Transformer (DDT) that captures local and global interactions in parallel, achieving state-of-the-art performance with significantly fewer computational costs.
Transformer is beneficial for image denoising tasks since it can model long-range dependencies to overcome the limitations presented by inductive convolutional biases. However, directly applying the transformer structure to remove noise is challenging because its complexity grows quadratically with the spatial resolution. In this paper, we propose an efficient Dual-branch Deformable Transformer (DDT) denoising network which captures both local and global interactions in parallel. We divide features with a fixed patch size and a fixed number of patches in local and global branches, respectively. In addition, we apply deformable attention operation in both branches, which helps the network focus on more important regions and further reduces computational complexity. We conduct extensive experiments on real-world and synthetic denoising tasks, and the proposed DDT achieves state-of-the-art performance with significantly fewer computational costs.