任意分辨率人脸超分新方法，支持任意缩放倍数。
Arbitrary-Resolution and Arbitrary-Scale Face Super-Resolution with Implicit Representation Networks
- 用坐标+特征预测像素值，实现任意缩放
- 提升高频纹理还原，减少模糊失真
- 适合需要灵活处理尺寸的面部图像任务
人脸超分辨率（FSR）是提升低分辨率人脸图像质量的关键技术，对人脸识别等应用具有重要意义。然而，现有方法受限于固定放大倍数且对输入尺寸变化敏感。本文提出基于隐式表示网络的任意分辨率与任意尺度人脸超分方法（ARASFSR），包含三项创新：首先，利用二维深度特征、局部相对坐标和上采样比例来预测目标像素的RGB值，实现任意放大倍数；其次，引入局部频率估计模块，捕捉高频人脸纹理信息，缓解频谱偏差问题；最后，设计全局坐标调制模块，引导模型利用先验人脸结构知识，有效实现分辨率自适应。定量与定性评估表明，ARASFSR在多种输入尺寸和放大倍数下均优于现有最优方法，具备更强鲁棒性。
原文摘要 · Abstract (English)
Face super-resolution (FSR) is a critical technique for enhancing low-resolution facial images and has significant implications for face-related tasks. However, existing FSR methods are limited by fixed up-sampling scales and sensitivity to input size variations. To address these limitations, this paper introduces an Arbitrary-Resolution and Arbitrary-Scale FSR method with implicit representation networks (ARASFSR), featuring three novel designs. First, ARASFSR employs 2D deep features, local relative coordinates, and up-sampling scale ratios to predict RGB values for each target pixel, allowing super-resolution at any up-sampling scale. Second, a local frequency estimation module captures high-frequency facial texture information to reduce the spectral bias effect. Lastly, a global coordinate modulation module guides FSR to leverage prior facial structure knowledge and achieve resolution adaptation effectively. Quantitative and qualitative evaluations demonstrate the robustness of ARASFSR over existing state-of-the-art methods while super-resolving facial images across various input sizes and up-sampling scales.
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。