GVTNet: Graph Vision Transformer For Face Super-Resolution

TL;DR

GVTNet introduces a graph neural network-based transformer architecture for face super-resolution, effectively modeling relationships between facial patches to improve the quality of super-resolved facial images.

Contribution

This paper presents a novel graph vision transformer that treats facial patches as graph nodes, enabling better modeling of facial component relationships for super-resolution.

Findings

Outperforms state-of-the-art methods in face super-resolution

Enhances facial component details more effectively

Demonstrates superior quantitative and visual results

Abstract

Recent advances in face super-resolution research have utilized the Transformer architecture. This method processes the input image into a series of small patches. However, because of the strong correlation between different facial components in facial images. When it comes to super-resolution of low-resolution images, existing algorithms cannot handle the relationships between patches well, resulting in distorted facial components in the super-resolution results. To solve the problem, we propose a transformer architecture based on graph neural networks called graph vision transformer network. We treat each patch as a graph node and establish an adjacency matrix based on the information between patches. In this way, the patch only interacts between neighboring patches, further processing the relationship of facial components. Quantitative and visualization experiments have underscored the superiority of our algorithm over state-of-the-art techniques. Through detailed comparisons, we have demonstrated that our algorithm possesses more advanced super-resolution capabilities, particularly in enhancing facial components. The PyTorch code is available at https://github.com/continueyang/GVTNet