发表机构
Brandeis University（布兰迪斯大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究人脸超分辨率问题，提出基于参考图像的解决方案，利用空间变换器对齐模块和聚合函数，实现高保真超分辨率，较小模型在多数据集达最优结果。
AI 中文摘要
人脸超分辨率是提高包含人脸图像分辨率以添加更精细细节的任务。它在许多计算机视觉应用中普遍存在，用户常未察觉。但因是不适定问题，高保真完成具挑战性。本文提出基于参考的人脸超分辨率解决方案，用高分辨率参考图像辅助。展示基于空间变换器的对齐模块，比流行的可变形卷积更稳定。还展示聚合函数，能在有可用参考图像时获取优质信息，无可用信息时抑制该功能。最后表明相对小的模型能在多个数据集上取得最优结果。
英文摘要
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.
DOI：10.1007/978-981-96-0911-6_24
