Conventional super-resolution methods suffer from two drawbacks: substantial
computational cost in upscaling an entire large image, and the introduction of
extraneous or potentially detrimental information for downstream computer
vision tasks during the refinement of the background. To solve these issues, we
propose a novel transformer-based algorithm, Selective Super-Resolution (SSR),
which partitions images into non-overlapping tiles, selects tiles of interest
at various scales with a pyramid architecture, and exclusively reconstructs
these selected tiles with deep features. Experimental results on three datasets
demonstrate the efficiency and robust performance of our approach for
super-resolution. Compared to the state-of-the-art methods, the FID score is
reduced from 26.78 to 10.41 with 40% reduction in computation cost for the
BDD100K dataset. The source code is available at
this https URL

通过将图像分割为不重叠的图块、使用金字塔结构选择感兴趣的图块，并利用深度特征仅重构这些选定的图块，我们提出了一种新颖的基于变压器的算法 Selective Super-Resolution（SSR），解决了常规超分辨率方法在放大整个大图像时的巨大计算成本和在背景细化过程中引入额外或可能有害信息的两个缺点。实验证明，我们的方法在超分辨率方面具备效率和稳健性，在 BDD100K 数据集上与最先进的方法相比，FID 评分从 26.78 降低到 10.41，计算成本减少了 40%。源代码可在此 https URL 获得。