Skip to content

Latest commit

 

History

History
188 lines (138 loc) · 14.7 KB

FaceRelated.md

File metadata and controls

188 lines (138 loc) · 14.7 KB
Raw

Face Restoration and Super-Resolution and other related topics. Archived

Table of Contents

Face Restoration

  • DR2: Diffusion-based Robust Degradation Remover for Blind Face Restoration
    Zhixin Wang, Xiaoyun Zhang, Ziying Zhang, Huangjie Zheng, Mingyuan Zhou, Ya Zhang, Yanfeng Wang
    [CVPR 2023] [Pytorch-Code]

  • Towards Robust Blind Face Restoration with Codebook Lookup Transformer
    Shangchen Zhou, Kelvin C.K. Chan, Chongyi Li, Chen Change Loy
    [NeuralIPS 2022] [Project] [Pytorch-Code]
    [CodeFormer] 🔥

  • VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder
    Yuchao Gu, Xintao Wang, Liangbin Xie, Chao Dong, Gen Li, Ying Shan, Ming-Ming Cheng
    [ECCV 2022 Oral] [Project] [Pytorch-Code]

  • RestoreFormer: High-Quality Blind Face Restoration from Undegraded Key-Value Pairs
    Zhouxia Wang, Jiawei Zhang, Runjian Chen, Wenping Wang, Ping Luo
    [CVPR 2022] [Pytorch-Code]

  • Progressive Semantic-Aware Style Transformation for Blind Face Restoration
    Chaofeng Chen, Xiaoming Li, Lingbo Yang, Xianhui Lin, Lei Zhang, Kwan-Yee K. Wong
    [CVPR 2021] [Pytorch-Code]
    [★] 用人脸图像和人脸解析结果预测scale和bias, 整体和SPADE的思路十分相似. 实测效果貌似不如HiFaceGAN.

  • GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior
    Xintao Wang, Yu Li, Honglun Zhang, Ying Shan
    [CVPR 2021] [Project] [Pytorch-Code]
    [★] 用预训练的人脸GAN网络提取的特征作为先验, 一个UNet型网络作为degradation removal模块, 从该模块中提取空间特征, 并用SFT的思想结合到先验特征上. 对五官分别使用了判别器.

  • Blind Face Restoration via Deep Multi-scale Component Dictionaries
    Xiaoming Li, Chaofeng Chen, Shangchen Zhou, Xianhui Lin, Wangmeng Zuo, Lei Zhang
    [ECCV 2020] [Pytorch-Code]
    [★★] (构建字典, 匹配最近邻特征) 对眼睛鼻子嘴建立字典, inference时通过匹配最相似的feature找到相似的高清特征并做替换. 字典通过VGG网络提特征和聚类实现. 实测对五官的增强效果不错, 不过对于头发皮肤等部分效果不明显.

  • Enhanced Blind Face Restoration With Multi-Exemplar Images and Adaptive Spatial Feature Fusion
    Xiaoming Li, Wenyu Li, Dongwei Ren, Hongzhi Zhang, Meng Wang, Wangmeng Zuo
    [CVPR 2020 Oral] [Code]
    [★] (基于同一张脸的exemplar做恢复) 通过关键点从数张同一人的examplar图像中选出最相思的图像, 使用moving least-square和AdaIn进行空间和亮度的对齐, 提出了ASFF模块通过预测attention map将引导图和LR图的特征融合

  • HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment
    Lingbo Yang, Chang Liu, Pan Wang, Shanshe Wang, Peiran Ren, Siwei Ma, Wen Gao
    [MM 2020] [Project] [Pytorch-Code]
    [★☆] 通过不同提取不同尺度的语义信息作为指导, 实现人脸修复, 对真实照片效果也还可以.

  • (CVPR 2018) Deep semantic face deblurring
    Ziyi Shen, Wei-Sheng Lai , Tingfa Xu, Jan Kautz, Ming-Hsuan Yang
    [CVPR 2018] [Project] [Matlab-Code]
    [★] 用一个人脸解析网络得到五官mask, 再把mask与输入结合, 分64和128两个分辨率尺度做deblur

  • Learning Warped Guidance for Blind Face Restoration
    Xiaoming Li, Ming Liu, Yuting Ye, Wangmeng Zuo, Liang Lin, Ruigang Yang
    [CVPR 2018] [Torch-Code]
    [★] (基于同一张脸的exemplar做恢复) 设计了WrapNet做对齐和RecNet做修复. WrapNet以exemplar和LR做输入, 关键点距离作为loss. RecNet接受LR和对齐后的exemplar, 使用全局和局部的gan loss以及VGG loss

  • Deep face deblurring
    Grigorios Chrysos, Stefanos Zafeiriou
    [CVPRW 2017]
    [☆]

Face SuperResolution

  • Spatial-Frequency Mutual Learning for Face Super-Resolution
    Chenyang Wang, Junjun Jiang, Zhiwei Zhong, Xianming Liu
    [CVPR 2023] [Pytorch-Code]

  • Learning Spatial Attention for Face Super-Resolution
    Chaofeng Chen, Dihong Gong, Hao Wang, Zhifeng Li, Kwan-Yee K. Wong
    [TIP 2020] [Pytorch-Code]
    [SPARNet] [★☆] 无语义先验的基于attention的人脸超分

  • Deep Face Super-Resolution with Iterative Collaboration between Attentive Recovery and Landmark Estimation
    Cheng Ma, Zhenyu Jiang, Yongming Rao, Jiwen Lu, Jie Zhou
    [CVPR 2020] [Pytorch-Code]
    [★☆] 迭代训练人脸超分和关键点网络, 并利用两个任务的信息, 相互优化

  • Learning to Have an Ear for Face Super-Resolution
    Givi Meishvili, Simon Jenni, Paolo Favaro
    [CVPR 2020] [Project]

  • Face Super-Resolution Guided by 3D Facial Priors
    Xiaobin Hu, Wenqi Ren, John LaMaster, Xiaochun Cao, Xiaoming Li, Zechao Li, Bjoern Menze, Wei Liu
    [ECCV 2020]

  • Component Attention Guided Face Super-Resolution Network: CAGFace
    Ratheesh Kalarot, Tao Li, Fatih Porikli
    [WACV 2020] [Pytorch-Code]
    [★] 利用人脸解析mask作为attention map的两阶段人脸超分

  • Progressive Face Super-Resolution via Attention to Facial Landmark
    Deokyun Kim, Minseon Kim, Gihyun Kwon, Dae-Shik Kim
    [BMVC 2019] [Pytorch-Code]
    [★☆] 一个结构简洁的渐进式人脸超分网络, 使用了额外的关键点检测网络作为计算loss的attention.

  • Exemplar Guided Face Image Super-Resolution without Facial Landmarks
    Berk Dogan, Shuhang Gu, Radu Timofte
    [CVPRW 2019] [Pytorch-Code]
    [★] 用一张相同人的照片作为引导图, 将引导图通过一个可学习的warp net与输入图像对齐, 之后将原图和warped guidance经过一个网络生成超分结果. 使用了GAN loss, VGG loss以及identity loss等.

  • FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors
    Yu Chen, Ying Tai, Xiaoming Liu, Chunhua Shen, Jian Yang
    [CVPR 2018] [Torch-Code]
    [★] 一个分支预测lanmark和分割结果, 辅助人脸超分

  • Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs
    Adrian Bulat, Georgios Tzimiropoulos
    [CVPR 2018] [Pytorch-Code]
    [★] 同时做SR和关键点检测

  • To learn image super-resolution, use a GAN to learn how to do image degradation first
    Adrian Bulat, Jing Yang, Georgios Tzimiropoulos
    [ECCV 2018] [Pytorch-Code]
    [★] 先用GAN预测一个降质网络, 估计真实LR数据, 再训练超分模型

  • Face Super-resolution Guided by Facial Component Heatmaps
    Xin Yu, Basura Fernando, Bernard Ghanem, Fatih Porikli, Richard Hartley
    [ECCV 2018]
    [★] 结合人脸关键点的heapmap信息做人脸超分

  • Attention-Aware Face Hallucination via Deep Reinforcement Learning
    Qingxing Cao, Liang Lin, Yukai Shi, Xiaodan Liang, Guanbin Li
    [CVPR 2017] [Torch-Code]

  • Learning to Super-resolve Blurry Face and Text Images
    Xiangyu Xu, Deqing Sun, Jinshan Pan, Yujin Zhang, Hanspeter Pfister, Ming-Hsuan Yang
    [ICCV 2017] [Project]

Face Manipulation

Others