Saved in:
Bibliographic Details
Main Authors: Yang, Chao, Fan, Yong, Lu, Cheng, Yuan, Minghao, Yang, Zhijing
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.12570
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929718916284416
author Yang, Chao
Fan, Yong
Lu, Cheng
Yuan, Minghao
Yang, Zhijing
author_facet Yang, Chao
Fan, Yong
Lu, Cheng
Yuan, Minghao
Yang, Zhijing
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2502_12570
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GVTNet: Graph Vision Transformer For Face Super-Resolution
Yang, Chao
Fan, Yong
Lu, Cheng
Yuan, Minghao
Yang, Zhijing
Computer Vision and Pattern Recognition
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
title GVTNet: Graph Vision Transformer For Face Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.12570