Dual Recovery Network with Online Compensation for Image Super-Resolution

TL;DR

This paper introduces a dual high-frequency recovery network that leverages online retrieved data and internal inference to improve image super-resolution, effectively recovering lost high-frequency details.

Contribution

The paper proposes a novel dual high-frequency recovery network that combines internal inference and external online data retrieval for enhanced super-resolution.

Findings

DHN outperforms state-of-the-art SR methods

Effective recovery of high-frequency details

Utilizes online retrieved references for better results

Abstract

Image super-resolution (SR) methods essentially lead to a loss of some high-frequency (HF) information when predicting high-resolution (HR) images from low-resolution (LR) images without using external references. To address this issue, we additionally utilize online retrieved data to facilitate image SR in a unified deep framework. A novel dual high-frequency recovery network (DHN) is proposed to predict an HR image with three parts: an LR image, an internal inferred HF (IHF) map (HF missing part inferred solely from the LR image) and an external extracted HF (EHF) map. In particular, we infer the HF information based on both the LR image and similar HR references which are retrieved online. For the EHF map, we align the references with affine transformation and then in the aligned references, part of HF signals are extracted by the proposed DHN to compensate for the HF loss. Extensive experimental results demonstrate that our DHN achieves notably better performance than state-of-the-art SR methods.