Attention-Guided Multi-scale Interaction Network for Face Super-Resolution

TL;DR

This paper introduces AMINet, a novel face super-resolution network that effectively fuses multiscale features using attention mechanisms, leading to improved performance and efficiency over existing hybrid CNN-Transformer methods.

Contribution

The paper proposes a new multiscale interaction network with specialized modules for feature fusion, enhancing face super-resolution by promoting feature complementarity and reducing computational costs.

Findings

Achieves superior super-resolution quality on benchmark datasets.

Operates with less computational cost and faster inference.

Effectively fuses local and global features through attention mechanisms.

Abstract

Recently, CNN and Transformer hybrid networks demonstrated excellent performance in face super-resolution (FSR) tasks. Since numerous features at different scales in hybrid networks, how to fuse these multiscale features and promote their complementarity is crucial for enhancing FSR. However, existing hybrid network-based FSR methods ignore this, only simply combining the Transformer and CNN. To address this issue, we propose an attention-guided Multiscale interaction network (AMINet), which incorporates local and global feature interactions, as well as encoder-decoder phase feature interactions. Specifically, we propose a Local and Global Feature Interaction Module (LGFI) to promote the fusion of global features and the local features extracted from different receptive fields by our Residual Depth Feature Extraction Module (RDFE). Additionally, we propose a Selective Kernel Attention Fusion Module (SKAF) to adaptively select fusions of different features within the LGFI and encoder-decoder phases. Our above design allows the free flow of multiscale features from within modules and between the encoder and decoder, which can promote the complementarity of different scale features to enhance FSR. Comprehensive experiments confirm that our method consistently performs well with less computational consumption and faster inference.