计算机科学
利用
变压器
人工智能
水准点(测量)
像素
图像复原
降噪
图像压缩
模式识别(心理学)
图像(数学)
计算机视觉
图像处理
工程类
计算机安全
电气工程
大地测量学
电压
地理
作者
Xiangyu Chen,Xintao Wang,Wenlong Zhang,Xiangtao Kong,Yu Qiao,Jiantao Zhou,Dong Chen
出处
期刊:Cornell University - arXiv
日期:2023-01-01
标识
DOI:10.48550/arxiv.2309.05239
摘要
Transformer-based methods have shown impressive performance in image restoration tasks, such as image super-resolution and denoising. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better restoration, we propose a new Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to further exploit the potential of the model for further improvement. Extensive experiments have demonstrated the effectiveness of the proposed modules. We further scale up the model to show that the performance of the SR task can be greatly improved. Besides, we extend HAT to more image restoration applications, including real-world image super-resolution, Gaussian image denoising and image compression artifacts reduction. Experiments on benchmark and real-world datasets demonstrate that our HAT achieves state-of-the-art performance both quantitatively and qualitatively. Codes and models are publicly available at https://github.com/XPixelGroup/HAT.
科研通智能强力驱动
Strongly Powered by AbleSci AI