Learning A Single Network for Scale-Arbitrary Super-Resolution
arXiv:2004.03791
Abstract
Recently, the performance of single image super-resolution (SR) has been significantly improved with powerful networks. However, these networks are developed for image SR with a single specific integer scale (e.g., x2;x3,x4), and cannot be used for non-integer and asymmetric SR. In this paper, we propose to learn a scale-arbitrary image SR network from scale-specific networks. Specifically, we propose a plug-in module for existing SR networks to perform scale-arbitrary SR, which consists of multiple scale-aware feature adaption blocks and a scale-aware upsampling layer. Moreover, we introduce a scale-aware knowledge transfer paradigm to transfer knowledge from scale-specific networks to the scale-arbitrary network. Our plug-in module can be easily adapted to existing networks to achieve scale-arbitrary SR. These networks plugged with our module can achieve promising results for non-integer and asymmetric SR while maintaining state-of-the-art performance for SR with integer scale factors. Besides, the additional computational and memory cost of our module is very small.
arXiv commentAccepted by ICCV 2021
References in corpus (7)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Sketch-based Manga Retrieval using Manga109 Dataset
- Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
- CondConv: Conditionally Parameterized Convolutions for Efficient Inference
- MemNet: A Persistent Memory Network for Image Restoration
- DyNet: Dynamic Convolution for Accelerating Convolutional Neural Networks
- Learning a Single Convolutional Super-Resolution Network for Multiple Degradations