Cross-Scale Internal Graph Neural Network for Image Super-Resolution

TL;DR

This paper introduces a cross-scale internal graph neural network that leverages multi-scale patch recurrence to improve image super-resolution by passing high-resolution cues across different scales within the same image.

Contribution

The paper proposes a novel cross-scale internal graph neural network that exploits cross-scale patch recurrence for enhanced image super-resolution, integrating internal and external information.

Findings

Outperforms state-of-the-art SISR methods on standard benchmarks.

Effectively utilizes cross-scale patch recurrence for texture detail recovery.

Demonstrates significant improvements over existing non-local networks.

Abstract

Non-local self-similarity in natural images has been well studied as an effective prior in image restoration. However, for single image super-resolution (SISR), most existing deep non-local methods (e.g., non-local neural networks) only exploit similar patches within the same scale of the low-resolution (LR) input image. Consequently, the restoration is limited to using the same-scale information while neglecting potential high-resolution (HR) cues from other scales. In this paper, we explore the cross-scale patch recurrence property of a natural image, i.e., similar patches tend to recur many times across different scales. This is achieved using a novel cross-scale internal graph neural network (IGNN). Specifically, we dynamically construct a cross-scale graph by searching k-nearest neighboring patches in the downsampled LR image for each query patch in the LR image. We then obtain the corresponding k HR neighboring patches in the LR image and aggregate them adaptively in accordance to the edge label of the constructed graph. In this way, the HR information can be passed from k HR neighboring patches to the LR query patch to help it recover more detailed textures. Besides, these internal image-specific LR/HR exemplars are also significant complements to the external information learned from the training dataset. Extensive experiments demonstrate the effectiveness of IGNN against the state-of-the-art SISR methods including existing non-local networks on standard benchmarks.