Super-FAN是一种基于GAN的创新方法，它结合了面部结构信息，集成了子网络进行面部对齐和优化新颖的热图损失。此方法不仅提升了真实世界中任意姿势下低分辨率面部图像的质量，还能准确地定位这些低质量图像上的面部关键点。与以往工作不同，Super-FAN不仅适用于正面图像，还覆盖了各种面部角度，并且在真实世界图像上表现出色。
Title: Super-FAN: Integrated facial landmark localization and super-resolution of
real-world low resolution faces in arbitrary poses with GANs
CVPR 2018 spotlight
Addresses 2 challenging tasks：
- improving the quality of low resolution facial images accurately
- locating the facial landmarks on such poor resolution images
Novelty：
-
Super-FAN(based on GAN): incorporating structural information
integrating a sub-network forintegrating a sub-network for
face alignment through heatmap regression and optimizing a novel
heatmap loss -
benefit：not only on frontal images(正脸) but on the whole spectrum of facial poses
not only on synthetic low resolution images (as in prior work) but also on real-world images.
扫一扫
3198
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
