用图神经网络增强面部超分，让人脸细节更自然
GVTNet: Graph Vision Transformer For Face Super-Resolution
- 将图像块视为节点构建图结构，只与邻近块交互
- 在多个数据集上提升峰值信噪比，面部特征更清晰
- 适合需要高保真人脸重建的应用场景
面部超分辨率研究近年采用Transformer架构，将输入图像划分为多个小块进行处理。然而，由于人脸不同部件间存在强相关性，现有算法难以有效建模块间关系，导致超分结果中面部结构失真。为此，我们提出基于图神经网络的视觉变压器网络（GVTNet），将每个图像块视为图节点，并根据块间信息构建邻接矩阵，使块仅与邻近块交互，从而更好地捕捉面部组件间的关联。定量和可视化实验表明，该方法优于当前最先进的技术，在提升面部特征方面表现更优。代码已开源。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。