2022-08-20

translated by 谷歌翻译

2022-07-12

translated by 谷歌翻译

2022-07-28

translated by 谷歌翻译

2022-07-12

translated by 谷歌翻译

2021-06-06

translated by 谷歌翻译

2021-12-04

translated by 谷歌翻译

2022-10-04
Recently, Transformer-based image restoration networks have achieved promising improvements over convolutional neural networks due to parameter-independent global interactions. To lower computational cost, existing works generally limit self-attention computation within non-overlapping windows. However, each group of tokens are always from a dense area of the image. This is considered as a dense attention strategy since the interactions of tokens are restrained in dense regions. Obviously, this strategy could result in restricted receptive fields. To address this issue, we propose Attention Retractable Transformer (ART) for image restoration, which presents both dense and sparse attention modules in the network. The sparse attention module allows tokens from sparse areas to interact and thus provides a wider receptive field. Furthermore, the alternating application of dense and sparse attention modules greatly enhances representation ability of Transformer while providing retractable attention on the input image.We conduct extensive experiments on image super-resolution, denoising, and JPEG compression artifact reduction tasks. Experimental results validate that our proposed ART outperforms state-of-the-art methods on various benchmark datasets both quantitatively and visually. We also provide code and models at the website https://github.com/gladzhang/ART.
translated by 谷歌翻译

2022-08-31

translated by 谷歌翻译

2022-11-30
Image super-resolution (SR) serves as a fundamental tool for the processing and transmission of multimedia data. Recently, Transformer-based models have achieved competitive performances in image SR. They divide images into fixed-size patches and apply self-attention on these patches to model long-range dependencies among pixels. However, this architecture design is originated for high-level vision tasks, which lacks design guideline from SR knowledge. In this paper, we aim to design a new attention block whose insights are from the interpretation of Local Attribution Map (LAM) for SR networks. Specifically, LAM presents a hierarchical importance map where the most important pixels are located in a fine area of a patch and some less important pixels are spread in a coarse area of the whole image. To access pixels in the coarse area, instead of using a very large patch size, we propose a lightweight Global Pixel Access (GPA) module that applies cross-attention with the most similar patch in an image. In the fine area, we use an Intra-Patch Self-Attention (IPSA) module to model long-range pixel dependencies in a local patch, and then a $3\times3$ convolution is applied to process the finest details. In addition, a Cascaded Patch Division (CPD) strategy is proposed to enhance perceptual quality of recovered images. Extensive experiments suggest that our method outperforms state-of-the-art lightweight SR methods by a large margin. Code is available at https://github.com/passerer/HPINet.
translated by 谷歌翻译

2021-11-18

translated by 谷歌翻译

2021-12-31

translated by 谷歌翻译

2022-01-09

translated by 谷歌翻译

2022-09-05

translated by 谷歌翻译

2022-07-11

translated by 谷歌翻译

2022-07-21

translated by 谷歌翻译

2021-09-15

translated by 谷歌翻译

2021-11-29

translated by 谷歌翻译

2022-06-14

translated by 谷歌翻译

2021-12-17

translated by 谷歌翻译

2021-11-18

translated by 谷歌翻译
${authors} 分类：${tags}
${pubdate}${abstract_cn}
translated by 谷歌翻译