Hierarchical Similarity Learning for Aliasing Suppression Image Super-Resolution

TL;DR

This paper introduces HSRNet, a hierarchical super-resolution network that leverages self-similarity and multi-level attention to suppress aliasing effects in single image super-resolution, improving both visual quality and quantitative metrics.

Contribution

The paper proposes a novel hierarchical exploration block and multi-level spatial attention within an iterative optimization framework for enhanced aliasing suppression in SISR.

Findings

HSRNet outperforms existing methods in quantitative metrics.

The model effectively reduces aliasing artifacts.

Visual results show clearer textures and details.

Abstract

As a highly ill-posed issue, single image super-resolution (SISR) has been widely investigated in recent years. The main task of SISR is to recover the information loss caused by the degradation procedure. According to the Nyquist sampling theory, the degradation leads to aliasing effect and makes it hard to restore the correct textures from low-resolution (LR) images. In practice, there are correlations and self-similarities among the adjacent patches in the natural images. This paper considers the self-similarity and proposes a hierarchical image super-resolution network (HSRNet) to suppress the influence of aliasing. We consider the SISR issue in the optimization perspective, and propose an iterative solution pattern based on the half-quadratic splitting (HQS) method. To explore the texture with local image prior, we design a hierarchical exploration block (HEB) and progressive increase the receptive field. Furthermore, multi-level spatial attention (MSA) is devised to obtain the relations of adjacent feature and enhance the high-frequency information, which acts as a crucial role for visual experience. Experimental result shows HSRNet achieves better quantitative and visual performance than other works, and remits the aliasing more effectively.