arxiv2020
Human Motion Transfer with 3D Constraints and Detail Enhancement [link]arxiv2020
Human Motion Transfer from Poses in the Wild [link]arxiv2020
TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting [link][code]WACV2020
Do As I Do: Transferring Human Motion and Appearance between Monocular Videos with Spatial and Temporal Constraints [link]arxiv2019
Music-oriented Dance Video Synthesis with Pose Perceptual Loss [code]arxiv2019
Appearance Composing GAN: A General Method for Appearance-Controllable Human Video Motion Transfer[link]NeurIPS2019
Dancing to Music [code]ICCV2019
Everybody Dance Now [link][code]SIGGRAPH2019
Learning Character-Agnostic Motion for Motion Retargeting in 2D [link][code]SIGGRAPH2019
Neural Animation and Reenactment of Human Actor Videos [link]EG2019
Deep Video-Based Performance Cloning [link]
- Head2Head: Video-based Neural Head Synthesis [code]
- Head2Head++: Deep Facial Attributes Re-Targeting [code]
- MakeItTalk: Speaker-Aware Talking Head Animation [link]
- Audio-driven Talking Face Video Generation with Natural Head Pose [link]
arxiv2020
Everybody’s Talkin’: Let Me Talk as You Want [link]AAAI2020
MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targets [link]ICCV2019
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models [link][code][code]SIGASIA2019
Neural Style-Preserving Visual Dubbing [lini]ICCV2019
Few-Shot Adversarial Learning of Realistic Neural Talking Head Models [link] [code]SIGGRAPH2018
Deep video portraits [link]SIGASIA2017
Bringing Portraits to Life [link]