用高分辨率参考图提升人脸超分质量，效果更真实。
Reference-Based Face Super-Resolution Using the Spatial Transformer
- 引入空间变换器实现图像对齐，比可变形卷积更稳定。
- 设计自适应聚合函数，能有效利用参考图信息或自动屏蔽干扰。
- 小模型达到顶尖水平，适合实际部署应用。
人脸超分辨率旨在提升含人脸图像的分辨率并添加细节，是众多计算机视觉应用中的常见任务。然而，由于该问题病态性，实现高质量重建极具挑战。本文提出一种基于参考图的人脸超分辨率方法，利用高分辨率参考图像辅助生成。设计基于空间变换器的对齐模块，显著优于流行的可变形卷积；提出一种自适应聚合函数，在有高质量参考图时融合其信息，否则主动抑制干扰。实验表明，该轻量级模型在多个数据集上达到当前最优性能。源代码已公开于 https://github.com/varun-jois/FSRST。
原文摘要 · Abstract (English)
Face super-resolution is the task of increasing the resolution of an image containing a face thereby adding finer detail. It is a ubiquitous task in many computer vision applications and quite often the user isn't even aware that it is being performed. However, doing it with high fidelity is challenging as it is an ill-posed problem. In this paper we present a reference-based solution for face super-resolution that uses higher resolution reference images to aid in the task. We show an alignment module based on the spatial transformer that is considerably more stable than the popular deformable convolutions. We also show an aggregation function that can take good quality information from the reference images when available or suppress the function when such information is unavailable. Finally, we show that our relatively smaller model can achieve state of the art results on multiple datasets. The source code is available at https://github.com/varun-jois/FSRST.
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。