一个简单的插件转换图像到任意比例
A Simple Plugin for Transforming Images to Arbitrary Scales
摘要：
现有的超分辨率模型通常专门用于一个尺度，从根本上限制了它们在实际场景中的使用。在本文中，我们的目标是开发一个通用的插件，可以插入到现有的超分辨率模型，方便地增强其对任意分辨率图像缩放的能力，因此被称为ARIS。本文的主要贡献如下：（i）提出了一个基于transformer的插件模块，该模块以空间坐标为查询对象，通过交叉注意迭代地关注低分辨率图像特征，并输出查询空间位置的视觉特征，类似于图像的隐式表示;（ii）我们引入了一个新的自我监督训练计划，利用一致性约束，有效地增强模型对图像进行上采样的能力，使其达到不可见的尺度，即无法获得地面实况高分辨率图像;（iii）不失一般性，我们将所提出的ARIS插件模块注入到几个现有模型中，即IPT、SwinIR和HAT，表明所得模型不仅可以在固定比例因子上保持其原始性能，而且可以外推到看不见的尺度，在标准基准上大大优于现有的任何尺度超分辨率模型，例如Urban 100、DIV 2K等。
英文摘要：
Existing models on super-resolution often specialized for one scale, fundamentally limiting their use in practical scenarios. In this paper, we aim to develop a general plugin that can be inserted into existing super-resolution models, conveniently augmenting their ability towards Arbitrary Resolution Image Scaling, thus termed ARIS. We make the following contributions: (i) we propose a transformer-based plugin module, which uses spatial coordinates as query, iteratively attend the low-resolution image feature through cross-attention, and output visual feature for the queried spatial location, resembling an implicit representation for images; (ii) we introduce a novel self-supervised training scheme, that exploits consistency constraints to effectively augment the model's ability for upsampling images towards unseen scales, i.e. ground-truth high-resolution images are not available; (iii) without loss of generality, we inject the proposed ARIS plugin module into several existing models, namely, IPT, SwinIR, and HAT, showing that the resulting models can not only maintain their original performance on fixed scale factor but also extrapolate to unseen scales, substantially outperforming existing any-scale super-resolution models on standard benchmarks, e.g. Urban100, DIV2K, etc.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
