论文标题
CIAOSR:任意尺度图像超分辨率的连续隐式注意力集中网络
CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution
论文作者
论文摘要
学习连续图像表示最近在图像超分辨率(SR)中获得了普及,因为它具有从低分辨率输入中重建使用任意尺度的高分辨率图像的能力。现有方法主要是在SR图像中任何查询的坐标中预测新像素的附近功能。这样的本地合奏受到了一些局限性:i)它没有可学习的参数,并且忽略了视觉特征的相似性; ii)它具有有限的接收场,无法在图像中很重要的大磁场中的集合相关特征。为了解决这些问题,本文提出了一个名为Ciaosr的连续隐性注意力网络。我们明确设计一个隐性的注意网络,以了解附近本地功能的合奏权重。此外,我们在此隐式注意力网络中嵌入了量表感知的注意力,以利用其他非本地信息。基准数据集上的广泛实验证明,CIAOSR的表现明显优于具有相同主链的现有单个图像SR方法。此外,CIAOSR还实现了任意规模SR任务的最新性能。该方法的有效性也在现实世界的SR设置上证明。更重要的是,可以将CIAOSR灵活地集成到任何骨架中以提高SR性能。
Learning continuous image representations is recently gaining popularity for image super-resolution (SR) because of its ability to reconstruct high-resolution images with arbitrary scales from low-resolution inputs. Existing methods mostly ensemble nearby features to predict the new pixel at any queried coordinate in the SR image. Such a local ensemble suffers from some limitations: i) it has no learnable parameters and it neglects the similarity of the visual features; ii) it has a limited receptive field and cannot ensemble relevant features in a large field which are important in an image. To address these issues, this paper proposes a continuous implicit attention-in-attention network, called CiaoSR. We explicitly design an implicit attention network to learn the ensemble weights for the nearby local features. Furthermore, we embed a scale-aware attention in this implicit attention network to exploit additional non-local information. Extensive experiments on benchmark datasets demonstrate CiaoSR significantly outperforms the existing single image SR methods with the same backbone. In addition, CiaoSR also achieves the state-of-the-art performance on the arbitrary-scale SR task. The effectiveness of the method is also demonstrated on the real-world SR setting. More importantly, CiaoSR can be flexibly integrated into any backbone to improve the SR performance.