Learning from Multi-Perception Features for Real-Word Image Super-resolution
This work addresses the challenge of handling diverse perceptual characteristics in real-world image super-resolution, which is important for applications like photography and computer vision, though it appears incremental as it builds on existing blind-based approaches.
The authors tackled the problem of real-world image super-resolution by proposing MPF-Net, which leverages multiple perceptual features to overcome limitations in existing methods, achieving significant performance improvements over state-of-the-art methods on challenging datasets.
Currently, there are two popular approaches for addressing real-world image super-resolution problems: degradation-estimation-based and blind-based methods. However, degradation-estimation-based methods may be inaccurate in estimating the degradation, making them less applicable to real-world LR images. On the other hand, blind-based methods are often limited by their fixed single perception information, which hinders their ability to handle diverse perceptual characteristics. To overcome this limitation, we propose a novel SR method called MPF-Net that leverages multiple perceptual features of input images. Our method incorporates a Multi-Perception Feature Extraction (MPFE) module to extract diverse perceptual information and a series of newly-designed Cross-Perception Blocks (CPB) to combine this information for effective super-resolution reconstruction. Additionally, we introduce a contrastive regularization term (CR) that improves the model's learning capability by using newly generated HR and LR images as positive and negative samples for ground truth HR. Experimental results on challenging real-world SR datasets demonstrate that our approach significantly outperforms existing state-of-the-art methods in both qualitative and quantitative measures.