2019-07-02 论文分类

一 论文学习

根据网址（https://www.jianshu.com/p/6d761f8a8149）里提供的近年来计算机视觉会议上相关论文，和谷歌学术搜索整理筛选出现阶段需要的部分，主要的方向有三个，跟面部有关，与多帧图像有关，生成式对抗网络有关，与残差网络相关.

暑假主要需要阅读研究的是与多帧图像有关的论文

多帧图像相关

Deep multi-frame face super-resolution
E. Ustinova, V. Lempitsky
[pdf]

Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution
Yan Huang,Wei Wang,Liang Wang
[pdf]

[pdf]

Multi-FrameVideoSuper ResolutionUsingConvolutionalNeuralNetworks
[pdf]

面部有关

Face Super-resolution Guided by Facial Component Heatmaps
Xin Yu, Basura Fernando, Bernard Ghanem, Fatih Porikli, Richard Hartley
[pdf]

Super-FAN: Integrated Facial Landmark Localization and Super-Resolution of Real-World Low Resolution Faces in Arbitrary Poses With GANs
Adrian Bulat, Georgios Tzimiropoulos
[pdf] [Supp]

FSRNet: End-to-End Learning Face Super-Resolution With Facial Priors

Joint-Feature Guided Depth Map Super-Resolution With Face Priors
Shuai Yang, Jiaying Liu, Yuming Fang, and Zongming Guo
IEEE Trans. on Cybernetics (TCYB), Vol.48, No.1, pp.399-411, Jan. 2018.
[project]

残差网络

Image Super-Resolution Using Very Deep Residual Channel Attention Networks
Yulun Zhang, Kunpeng Li, Kai Li, Lichen Wang, Bineng Zhong, Yun Fu
[pdf]

Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network
Namhyuk Ahn, Byungkon Kang, Kyung-Ah Sohn
[pdf]

Multi-scale Residual Network for Image Super-Resolution
Juncheng Li, Faming Fang, Kangfu Mei, Guixu Zhang
[pdf]

生成式对抗网络

To learn image super-resolution, use a GAN to learn how to do image degradation first
Adrian Bulat, Jing Yang, Georgios Tzimiropoulos
[pdf]

Super-FAN: Integrated Facial Landmark Localization and Super-Resolution of Real-World Low Resolution Faces in Arbitrary Poses With GANs
Adrian Bulat, Georgios Tzimiropoulos
[pdf] [Supp]