AIGC生成论文汇总
1.1 无特定身份人物生成（Non-identity Generation）
(1) 变分自动编码器（Variational Auto-Encoder）
2022, CVPR,Shunyu Yao, RuiZhe Zhong, Yichao Yan, Guangtao Zhai, Xiaokang Yang,DFA-NeRF: Personalized Talking Head Generation via Disentangled Face Attributes Neural Rendering(DFA-NeRF：通过分离的人脸属性神经渲染生成个性化的说话头)
2021, CVPR,Daniel, Tal, and Aviv Tamar,Soft-IntroVAE: Analyzing and Improving the Introspective Variational Autoencoder(Soft-IntroVAE：分析和改进自省的变异性 自动编码器)
2020, Pattern Recognition,Na Liu, Tao Zhou, Yunfeng Ji, Ziyi Zhao, Lihong Wan,Synthesizing talking faces from text and audio: an autoencoder and sequence-to-sequence convolutional neural network(从文本和音频合成说话的面孔：自动编码器和序列到序列的卷积神经网络)
(2) 生成对抗网络（Generative Adversarial Network）
2022, CVPR, Sparse to Dense Dynamic 3D Facial Expression Generation（稀疏到密集的动态 3D 面部表情生成）
2022, CVPR, TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing(TransEditor: 基于变换器的双空间GAN用于高度可控的面部编辑)
2021, CVPR, Jinsong Zhang, Kun Li, Yu-Kun Lai, Jingyu Yang, PISE: Person Image Synthesis and Editing with Decoupled GAN(PISE：使用解耦 GAN 进行人物图像合成和编辑)
2021, CVPR, Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction（Fast-GANFIT：用于高保真 3D 人脸重建的生成对抗网络）
2020,IEEE Access,Y. Fan, Y. Liu, G. Lv, S. Liu, G. Li and Y. Huang, “Full Face-and-Head 3D Model With Photorealistic Texture,”(具有逼真纹理的全脸和头部 3D 模型)
2019, CVPR, GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction(GANFIT：用于高保真 3D 人脸重建的生成对抗网络拟合)
1.2 身份转换（Identity Swap）
(1) 不可知论者Subject-Agnostic
2022, CVPR,Qi Li, Weining Wang, Chengzhong Xu, Zhenan Sun,FaceSwapper: Learning Disentangled Representation for One-shot Progressive Face Swapping(FaceSwapper：学习用于一次性渐进式人脸交换的分离表示)
2022, CVPR,Yangyang Xu, Bailin Deng, Junle Wang, Yanqing Jing, Jia Pan, Shengfeng He,High-resolution Face Swapping via Latent Semantics Disentanglement(通过潜在语义解缠结实现高分辨率人脸交换)
2022, CVPR,Chao Xu, Jiangning Zhang, Miao Hua, Qian He, Zili Yi, Yong Liu,Region-Aware Face Swapping(区域感知人脸交换)
2022,CVPR,Yuval Nirkin, Yosi Keller, Tal Hassner,FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment(FSGANv2：改进的与主题无关的人脸交换和重演)
2022, CVPR,Daniil Chesakov, Anastasia Maltseva, Alexander Groshev, Andrey Kuznetsov, Denis Dimitrov,A new face swap method for image and video domains: a technical report(一种新的图像和视频领域的人脸交换方法：技术报告)[有提到逐帧生成的问题]
2022, CVPR,Zhiliang Xu, Zhibin Hong, Changxing Ding, Zhen Zhu, Junyu Han, Jingtuo Liu, Errui Ding,MobileFaceSwap: A Lightweight Framework for Video Face Swapping(MobileFaceSwap：用于视频人脸交换的轻量级框架)
2021, CVPR,Shuai Yang, Kai Qiao,ShapeEditer: a StyleGAN Encoder for Face Swapping（ShapeEditer：用于人脸交换的 StyleGAN 编码器）
(2)面部遮挡（ Facial Occlusion）
2021,ICMRYiu-Ming Cheung, Mengke Li, and Rong Zou, Facial Structure Guided GAN for Identity-preserved Face Image De-occlusion.(面部结构引导的 GAN，用于身份保留的面部图像去遮挡。)
2020,CVPR,Delphine Poux, Benjamin Allaert, Nacim Ihaddadene, Ioan Marius Bilasco, Chaabane Djeraba, Mohammed Bennamoun,Dynamic Facial Expression Recognition under Partial Occlusion with Optical Flow Reconstruction(基于光流重构的部分遮挡下的动态面部表情识别)
(3) 鉴别身份（Discriminative Identity）
2019, CVPR, Learning Robust 3D Face Reconstruction and Discriminative Identity Representation(学习鲁棒的 3D 人脸重建和判别身份表示)
(4) Out of Distribution(OOD) generalization
1.3 面部重演（Face Reenactment）
(1) 表情重演Expression Reenactment
2022, CVPR,Zipeng Ye, Zhiyao Sun, Yu-Hui Wen, Yanan Sun, Tian Lv, Ran Yi, Yong-Jin Liu, Dynamic Neural Textures: Generating Talking-Face Videos with Continuously Controllable Expressions(动态神经纹理：生成具有连续可控表情的说话人脸视频)
2020,IVA,Chaona Chen, Oliver G. B. Garrod, Philippe G. Schyns, and Rachael E. Jack, Dynamic Face Movement Texture Enhances the Perceived Realism of Facial Expressions of Emotion. (动态面部运动纹理增强了情感面部表情的感知真实感)
2018, CVPR, Feifei Zhang, Tianzhu Zhang, Qirong Mao, Changsheng Xu,Joint Pose and Expression Modeling for Facial Expression Recognition(用于面部表情识别的联合姿势和表情建模)
(2) 说话人脸Talking Face
2022,CVPR,Fei Yin, Yong Zhang, Xiaodong Cun, Mingdeng Cao, Yanbo Fan, Xuan Wang, Qingyan Bai, Baoyuan Wu, Jue Wang, Yujiu Yang,StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN(StyleHEAT：通过预训练 StyleGAN 生成一次性高分辨率可编辑说话人脸)
2022,cvpr,Audio-Driven Talking Face Video Generation with Dynamic Convolution Kernels(使用动态卷积核生成音频驱动的说话人脸视频)
2021,CVPR,Chenxu Zhang, Yifan Zhao, Yifei Huang, Ming Zeng, Saifeng Ni, Madhukar Budagavi, Xiaohu Guo,FACIAL: Synthesizing Dynamic Talking Face with Implicit Attribute Learning(FACIAL：用隐式属性学习合成动态说话的脸)
2021,CVPR,Hang Zhou, Yasheng Sun, Wayne Wu, Chen Change Loy, Xiaogang Wang, Ziwei Liu,Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation(通过隐式模块化视听表示生成姿态可控的说话人脸)
2021,ICIG,Luchuan Song, Bin Liu & Nenghai Yu,Talking Face Video Generation with Editable Expression(具有可编辑表情的说话人脸视频生成)
2021,InterSpeech,Shijing Si, Jianzong Wang, Xiaoyang Qu, Ning Cheng, Wenqi Wei, Xinghua Zhu, Jing Xiao,Speech2Video: Cross-Modal Distillation for Speech to Video Generation(Speech2Video：语音到视频生成的跨模态蒸馏)
(3) 姿态重演Pose Reenactment
2021, CVPR,Linsen Song, Wayne Wu, Chaoyou Fu, Chen Qian, Chen Change Loy, Ran He, Everything’s Talkin’: Pareidolia Face Reenactment(一切都在谈论：Pareidolia 面部重演)
1.4 属性操作Attribute Manipulation
(1) 化妆Makeup
2021, AAAI,Zhiliang Xu, Xiyu Yu, Zhibin Hong, Zhen Zhu, Junyu Han, Jingtuo Liu, Errui Ding, Xiang Bai,FaceController: Controllable Attribute Editing for Face in the Wild(FaceController：野外人脸的可控属性编辑)
2018, ECCV,Taihong Xiao, Jiapeng Hong, Jinwen Ma,ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes(ELEGANT：使用 GAN 交换潜在编码以传输多个人脸属性)
(2)年龄 Age
2021,CVPR,Zhizhong Huang, Junping Zhang, Hongming Shan,When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework(当年龄不变的人脸识别遇到人脸年龄合成时：多任务学习框架)[学习年龄不变的身份相关表示，同时实现人脸合成]
2018, CVPR,Hongyu Yang, Di Huang, Yunhong Wang, Anil K. Jain,Learning Face Age Progression: A Pyramid Architecture of GANs(学习人脸年龄进展：GAN 的金字塔结构)
(3) General(hair,gender,beard,head,eye)
2022, CVPR,Ganglai Wang, Peng Zhang, Lei Xie, Wei Huang, Yufei Zha,Attention-Based Lip Audio-Visual Synthesis for Talking Face Generation in the Wild(用于野外说话人脸生成的基于注意力的嘴唇视听合成)
2021,CVPR,Yue Gao, Fangyun Wei, Jianmin Bao, Shuyang Gu, Dong Chen, Fang Wen, Zhouhui Lian,High-Fidelity and Arbitrary Face Editing(高保真任意人脸编辑)
2021,TCSVT,Lingyun Yu; Jun Yu; Mengyan Li; Qiang Ling, Multimodal Inputs Driven Talking Face Generation With Spatial–Temporal Dependency.(多模态输入驱动具有时空依赖性的说话人脸生成)[预测视频帧，光流对帧之间的时间依赖性进行建模]
2021,SIGGRAPH Asia,Jiaqi Hao, Shiguang Liu, and Qing Xu. Controlling Eye Blink for Talking Face Generation via Eye Conversion. (通过眼睛转换控制眨眼以生成说话人脸)
2021,ICVGIP,Sandika Biswas, Sanjana Sinha, Dipanjan Das, and Brojeshwar Bhowmick. Realistic talking face animation with speech-induced head motion. (具有语音诱导头部运动的逼真的说话面部动画。)
2018,CVPR,StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation(StarGAN：用于多域图像到图像转换的统一生成对抗网络)[专注于hair]
(4) Text face
2022,CVPR,Mohamed Shawky Sabae, Mohamed Ahmed Dardir, Remonda Talaat Eskarous, Mohamed Ramzy Ebbed,StyleT2F: Generating Human Faces from Textual Description Using StyleGAN2(StyleT2F：使用 StyleGAN2 从文本描述中生成人脸)
2022,CVPR,Jianxin Sun, Qiyao Deng, Qi Li, Muyi Sun, Min Ren, Zhenan Sun,AnyFace: Free-style Text-to-Face Synthesis and Manipulation(AnyFace：自由风格的文本到人脸合成和操作)
2020,TEMSMET,Rohan Wadhawan; Tanuj Drall; Shubham Singh; Shampa ChakravertyMulti-Attributed and Structured Text-to-Face Synthesis(多属性和结构化文本到人脸合成)
2021,CVPR,Oza, Manan, Sukalpa Chanda, and David Doermann. “Semantic Text-to-Face GAN-ST^ 2FG.” .(语义文本到人脸 GAN -ST^2FG)
2021, CVPR, Xia W, Yang Y, Xue J H, et al. Towards open-world text-guided face image generation and manipulation(迈向开放世界文本引导的人脸图像生成和操作)
2021, FG, Y. Zhou and N. Shimada, “Generative Adversarial Network for Text-to-Face Synthesis and Manipulation with Pretrained BERT Model,”(使用预训练的 BERT 模型进行文本到人脸合成和操作的生成对抗网络)
2021,FG,X. Qiao, Y. Han, Y. Wu and Z. Zhang, Progressive Text-to-Face Synthesis with Generative Adversarial Network,(具有生成对抗网络的渐进式文本到面部合成)
2021,IEEE,Khan, Muhammad Zeeshan and Jabeen, Saira and Khan, Muhammad Usman Ghani and Saba, Tanzila and Rehmat, Asim and Rehman, Amjad and Tariq, UsmanA Realistic Image Generation of Face From Text Description Using the Fully Trained Generative Adversarial Networks(使用完全训练的生成对抗网络从文本描述中生成真实的人脸图像)
1.5 异质合成Heterogeneous Synthesis
(1) 跨光谱Cross-spectral
2021,CVPR,Xing Di, Shuowen Hu, Vishal M. Patel,Heterogeneous Face Frontalization via Domain Agnostic Learning(基于领域不可知学习的异构人脸正面化)
(2) 素描视觉Sketch Visual
2021, CVPR,Jia Li, Zhaoyang Li, Jie Cao, Xingguang Song, Ran He,FaceInpainter: High Fidelity Face Adaptation to Heterogeneous Domains(FaceInpainter：对异构域的高保真人脸适应)
(3) 风格Style
2022,CVPR,Jia Li, Jie Cao, JunXian Duan, Ran He,Styleverse: Towards Identity Stylization across Heterogeneous Domains（Styleverse：跨异构领域的身份风格化）
2021,CVPR,BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation(BlendGAN：用于任意风格化人脸生成的隐式 GAN 混合)
2021,MM,Haozhe Wu, Jia Jia, Haoyu Wang, Yishun Dou, Chao Duan, and Qingshan Deng. Imitating Arbitrary Talking Style for Realistic Audio-Driven Talking Face Synthesis.(模仿任意说话风格进行逼真的音频驱动说话人脸合成)
2020,MIG,Christian Murphy, Sudhir Mudur, Daniel Holden, Marc-André Carbonneau, Donya Ghafourzadeh, and Andre Beauchamp. Appearance Controlled Face Texture Generation for Video Game Characters. (视频游戏角色的外观控制面部纹理生成)
(4) 超分辨率Super-resolution
2022,CVPR,Jingwen He, Wu Shi, Kai Chen, Lean Fu, Chao Dong,GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors（GCFSR：一种没有面部和 GAN 先验的生成且可控的面部超分辨率方法）
2021, CVPR,Zhimeng Zhang, Lincheng Li, Yu Ding, Changjie Fan,Flow-Guided One-Shot Talking Face Generation With a High-Resolution Audio-Visual Dataset(具有高分辨率视听数据集的流引导式一次性说话人脸生成)