Global Learnable Attention for Single Image Super-Resolution

TL;DR

This paper introduces a novel Global Learnable Attention mechanism for single image super-resolution that adaptively adjusts similarity scores of non-local textures, especially useful for severely damaged textures, leading to state-of-the-art results.

Contribution

The paper proposes a new learnable attention method that dynamically modifies similarity scores, incorporating low-similarity textures for improved super-resolution, and employs SB-LSH for computational efficiency.

Findings

Achieves state-of-the-art super-resolution performance across various degradation types.

Reduces computational complexity from quadratic to linear using SB-LSH.

Demonstrates the effectiveness of learnable similarity scores in repairing severely damaged textures.

Abstract

Self-similarity is valuable to the exploration of non-local textures in single image super-resolution (SISR). Researchers usually assume that the importance of non-local textures is positively related to their similarity scores. In this paper, we surprisingly found that when repairing severely damaged query textures, some non-local textures with low-similarity which are closer to the target can provide more accurate and richer details than the high-similarity ones. In these cases, low-similarity does not mean inferior but is usually caused by different scales or orientations. Utilizing this finding, we proposed a Global Learnable Attention (GLA) to adaptively modify similarity scores of non-local textures during training instead of only using a fixed similarity scoring function such as the dot product. The proposed GLA can explore non-local textures with low-similarity but more accurate details to repair severely damaged textures. Furthermore, we propose to adopt Super-Bit Locality-Sensitive Hashing (SB-LSH) as a preprocessing method for our GLA. With the SB-LSH, the computational complexity of our GLA is reduced from quadratic to asymptotic linear with respect to the image size. In addition, the proposed GLA can be integrated into existing deep SISR models as an efficient general building block. Based on the GLA, we constructed a Deep Learnable Similarity Network (DLSN), which achieves state-of-the-art performance for SISR tasks of different degradation types (e.g. blur and noise). Our code and a pre-trained DLSN have been uploaded to GitHub{\dag} for validation.