Author:
Shen Hao,Zhao Zhong-Qiu,Zhang Wandi
Abstract
In image denoising networks, feature scaling is widely used to enlarge the receptive field size and reduce computational costs. This practice, however, also leads to the loss of high-frequency information and fails to consider within-scale characteristics. Recently, dynamic convolution has exhibited powerful capabilities in processing high-frequency information (e.g., edges, corners, textures), but previous works lack sufficient spatial contextual information in filter generation. To alleviate these issues, we propose to employ dynamic convolution to improve the learning of high-frequency and multi-scale features. Specifically, we design a spatially enhanced kernel generation (SEKG) module to improve dynamic convolution, enabling the learning of spatial context information with a very low computational complexity. Based on the SEKG module, we propose a dynamic convolution block (DCB) and a multi-scale dynamic convolution block (MDCB). The former enhances the high-frequency information via dynamic convolution and preserves low-frequency information via skip connections. The latter utilizes shared adaptive dynamic kernels and the idea of dilated convolution to achieve efficient multi-scale feature extraction. The proposed multi-dimension feature integration (MFI) mechanism further fuses the multi-scale features, providing precise and contextually enriched feature representations. Finally, we build an efficient denoising network with the proposed DCB and MDCB, named ADFNet. It achieves better performance with low computational complexity on real-world and synthetic Gaussian noisy datasets. The source code is available at https://github.com/it-hao/ADFNet.
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Global routing between capsules;Pattern Recognition;2024-04
2. Rethinking Pan-Sharpening via Spectral-Band Modulation;IEEE Transactions on Geoscience and Remote Sensing;2024
3. Mutual Information-driven Triple Interaction Network for Efficient Image Dehazing;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26
4. Decoupled Cross-Scale Cross-View Interaction for Stereo Image Enhancement in the Dark;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26
5. Dynamic Grouped Interaction Network for Low-Light Stereo Image Enhancement;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26