In image super-resolution, both pixel-wise accuracy and perceptual fidelity are desirable. However, most deep learning methods only achieve high performance in one aspect due to the perception-distortion trade-off, and works that successfully balance the trade-off rely on fusing results from separately trained models with ad-hoc post-processing. In this paper, we propose a novel super-resolution model with a low-frequency constraint (LFc-SR), which balances the objective and perceptual quality through a single model and yields super-resolved images with high PSNR and perceptual scores. We further introduce an ADMM-based alternating optimization method for the non-trivial learning of the constrained model. Experiments showed that our method, without cumbersome post-processing procedures, achieved the state-of-the-art performance. The code is available at https://github.com/Yuehan717/PDASR.
翻译:在图像超分辨率方面,最好要有像素精度和感知忠诚,然而,大多数深层次的学习方法仅因感知扭曲取舍而在一个方面取得高性能,并成功地平衡权衡得失的工作依赖于分别训练的模型和临时热处理后处理的引信结果。在本文中,我们提出了一个具有低频限制的新颖的超分辨率模型(LFc-SR),该模型通过单一模型平衡目标和感知质量,并产生超解图像与高PSNR和感知分数。我们进一步采用了基于ADMMM的交替优化方法,用于对受限制模式进行非三角学习。实验表明,我们的方法在没有繁琐的处理后程序的情况下,实现了最先进的性能。该代码可在https://github.com/Yuehan717/PDASR查阅。