人脸重演论文合集 Collection of face Reenactment papers

简介

以下是我收集的一些有关人脸重演的论文，以时间线倒叙列出，相同年份的按字母顺序排列，欢迎各位查阅。我将在以后的日子慢慢更新，欢迎订阅。如果各位看官有想补充的论文，欢迎在评论区提出哦~ （主要提出最近几年的，老论文整已经有了一两篇，写发展现状凑字数已经行了）

论文

2024年

• 3D-Aware Talking-Head Video Motion Transfer (WACV): paper.

2023年

• DiffusionRig: Learning Personalized Priors for Facial Appearance Editing(CVPR 2023): paper. code.
  👆我觉得这个挺屌的，但是用作视频的话会闪。
• High-Fidelity and Freely Controllable Talking Head Video Generation(CVPR, 2023): paper. code. 👈他git上说不开源
• HR-Net: a landmark based high realistic face reenactment network (TCSVT, 2023): paper.
• MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation (CVPR, 2023) paper. code.

2022年

• Adaptive Affine Transformation(AdaAT): A Simple and Effective Operation for Spatial Misaligned Image Generation. (MM2022): paper. code.
  👆该作者发的DINet非常经典，其中用的就是AdaAT，我怀疑cv6的免训练数字人用的就是这个。
• Dual-Generator Face Reenactment (CVPR, 2022): paper. code
• Face2Faceρ: Real-Time High-Resolution One-Shot Face Reenactment: paper. code.
• Finding Directions in GAN’s Latent Space for Neural Face Reenactment (BMVC, 2022): paper. code.
• FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment (PAMI, 2022): paper.

2021年

• A unified framework for high fidelity face swap and expression reenactment (TCSVT, 2021): paper
• LI-Net: Large-Pose Identity-Preserving Face Reenactment Network (ICME, 2021): paper.
• One-shot Face Reenactment Using Appearance Adaptive Normalization (AAAI, 2021): paper.
• PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering (ICCV, 2021): paper.

2020年

• ActGAN: Flexible and Efficient One-shot Face Reenactment (IWBF, 2020): paper.
• First Order Motion Model for Image Animation (NIPS, 2020): paper. code.
  👆老经典了。
• FReeNet: Multi-Identity Face Reenactment (CVPR, 2020): paper. code.
• Learning Identity-Invariant Motion Representations for Cross-ID Face Reenactment(CVPR, 2020): paper
• MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets(AAAI, 2020): paper.
• Neural Head Reenactment with Latent Pose Descriptors(CVPR, 2020): paper. code.
• Realistic Face Reenactment via Self-Supervised Disentangling of Identity and Pose(AAAI, 2020): paper.
• StyleRig: Rigging StyleGAN for 3D Control over Portrait Images(CVPR2020): paper. page.

2019年

• FSGAN: Subject Agnostic Face Swapping and Reenactment (ICCV, 2019) paper. code.
• One-shot Face Reenactment (BMVC, 2019): paper. code.

2018年

• GANimation: Anatomically-aware Facial Animation from a Single Image (ECCV, 2018): paper. code.
• ReenactGAN: Learning to Reenact Faces via Boundary Transfer (ECCV, 2018): paper. code.

2017年

• Synthesizing Obama: learning lip sync from audio (TOG, 2017): paper.
  👆合着cv6的数字人借鉴了这篇文章啊

2016年

• Face2Face: Real-time Face Capture and Reenactment of RGB Videos (CVPR, 2016): paper.

结语

先写这么多。。。。
我有一个梦想。