Xformer: Hybrid X-Shaped Transformer for Image Denoising
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914690579300352 |
|---|---|
| author | Zhang, Jiale Zhang, Yulun Gu, Jinjin Dong, Jiahua Kong, Linghe Yang, Xiaokang |
| author_facet | Zhang, Jiale Zhang, Yulun Gu, Jinjin Dong, Jiahua Kong, Linghe Yang, Xiaokang |
| contents | In this paper, we present a hybrid X-shaped vision Transformer, named Xformer, which performs notably on image denoising tasks. We explore strengthening the global representation of tokens from different scopes. In detail, we adopt two types of Transformer blocks. The spatial-wise Transformer block performs fine-grained local patches interactions across tokens defined by spatial dimension. The channel-wise Transformer block performs direct global context interactions across tokens defined by channel dimension. Based on the concurrent network structure, we design two branches to conduct these two interaction fashions. Within each branch, we employ an encoder-decoder architecture to capture multi-scale features. Besides, we propose the Bidirectional Connection Unit (BCU) to couple the learned representations from these two branches while providing enhanced information fusion. The joint designs make our Xformer powerful to conduct global information modeling in both spatial and channel dimensions. Extensive experiments show that Xformer, under the comparable model complexity, achieves state-of-the-art performance on the synthetic and real-world image denoising tasks. We also provide code and models at https://github.com/gladzhang/Xformer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_06440 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Xformer: Hybrid X-Shaped Transformer for Image Denoising Zhang, Jiale Zhang, Yulun Gu, Jinjin Dong, Jiahua Kong, Linghe Yang, Xiaokang Computer Vision and Pattern Recognition In this paper, we present a hybrid X-shaped vision Transformer, named Xformer, which performs notably on image denoising tasks. We explore strengthening the global representation of tokens from different scopes. In detail, we adopt two types of Transformer blocks. The spatial-wise Transformer block performs fine-grained local patches interactions across tokens defined by spatial dimension. The channel-wise Transformer block performs direct global context interactions across tokens defined by channel dimension. Based on the concurrent network structure, we design two branches to conduct these two interaction fashions. Within each branch, we employ an encoder-decoder architecture to capture multi-scale features. Besides, we propose the Bidirectional Connection Unit (BCU) to couple the learned representations from these two branches while providing enhanced information fusion. The joint designs make our Xformer powerful to conduct global information modeling in both spatial and channel dimensions. Extensive experiments show that Xformer, under the comparable model complexity, achieves state-of-the-art performance on the synthetic and real-world image denoising tasks. We also provide code and models at https://github.com/gladzhang/Xformer. |
| title | Xformer: Hybrid X-Shaped Transformer for Image Denoising |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2303.06440 |