Meta-SR: A Magnification-Arbitrary Network for Super-Resolution

TLDR

Super‑resolution has advanced with deep convolutional neural networks, yet arbitrary‑scale super‑resolution has been largely neglected, as prior work treats each scale factor as a separate, inefficient task limited to integer factors. The authors propose Meta‑SR, a single‑model approach that addresses arbitrary‑scale (including non‑integer) super‑resolution. Meta‑SR replaces the conventional upscale module with a Meta‑Upscale Module that predicts filter weights conditioned on the desired scale factor, enabling continuous zooming of any low‑resolution image with a single model and is evaluated on standard single‑image super‑resolution benchmarks. Experiments demonstrate that Meta‑Upscale outperforms prior approaches on benchmark datasets.

Abstract

Recent research on super-resolution has achieved great success due to the development of deep convolutional neural networks (DCNNs). However, super-resolution of arbitrary scale factor has been ignored for a long time. Most previous researchers regard super-resolution of differentscale factors as independent tasks. They train a specific model for each scale factor which is inefficient in computing, and prior work only take the super-resolution of several integer scale factors into consideration. In this work,we propose a novel method called Meta-SR to firstly solve super-resolution of arbitrary scale factor (including non-integer scale factors) with a single model. In our Meta-SR,the Meta-Upscale Module is proposed to replace the traditional upscale module. For arbitrary scale factor, the Meta-Upscale Module dynamically predicts the weights of the up-scale filters by taking the scale factor as input and use these weights to generate the HR image of arbitrary size. For any low-resolution image, our Meta-SR can continuously zoomin it with arbitrary scale factor by only using a single model.We evaluated the proposed method through extensive experiments on widely used benchmark datasets on single image super-resolution. The experimental results show the superiority of our Meta-Upscale.