OverNet: Lightweight Multi-Scale Super-Resolution with Overscaling Network

TL;DR

OverNet is a lightweight, multi-scale super-resolution network that efficiently handles arbitrary scale factors with a single model, outperforming previous methods in benchmarks while using fewer parameters.

Contribution

It introduces a recursive feature extractor, an overscaling reconstruction module, and a multi-scale loss for improved generalization and efficiency in super-resolution tasks.

Findings

Outperforms state-of-the-art in benchmarks

Uses fewer parameters than previous methods

Effective for arbitrary scale super-resolution

Abstract

Super-resolution (SR) has achieved great success due to the development of deep convolutional neural networks (CNNs). However, as the depth and width of the networks increase, CNN-based SR methods have been faced with the challenge of computational complexity in practice. Moreover, most of them train a dedicated model for each target resolution, losing generality and increasing memory requirements. To address these limitations we introduce OverNet, a deep but lightweight convolutional network to solve SISR at arbitrary scale factors with a single model. We make the following contributions: first, we introduce a lightweight recursive feature extractor that enforces efficient reuse of information through a novel recursive structure of skip and dense connections. Second, to maximize the performance of the feature extractor we propose a reconstruction module that generates accurate high-resolution images from overscaled feature maps and can be independently used to improve existing architectures. Third, we introduce a multi-scale loss function to achieve generalization across scales. Through extensive experiments, we demonstrate that our network outperforms previous state-of-the-art results in standard benchmarks while using fewer parameters than previous approaches.