4 papers
A Self-supervised Motion Representation for Portrait Video Generation
Qiyuan Zhang, Chenyu Wu, Wenzhang Sun +4
Recent advancements in portrait video generation have been noteworthy. However, existing methods rely heavily on human priors and pre-trained generative models, Motion representati…
MotionStrata: Hierarchical Motion Latents for Compact Video Autoencoding
Huaize Liu, Wenzhang Sun, Chunfeng Wang +6
First-frame-conditioned video autoencoders represent a clip with persistent content and a compact motion code. Although this removes much of the appearance redundancy, the remainin…
MoEE: Mixture of Emotion Experts for Audio-Driven Portrait Animation
Huaize Liu, Wenzhang Sun, Donglin Di +4
The generation of talking avatars has achieved significant advancements in precise audio synchronization. However, crafting lifelike talking head videos requires capturing a broad…
Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignment
Shuaiying Hou, Hongyu Tao, Junheng Fang +3
Learning 3D human motion from 2D inputs is a fundamental task in the realms of computer vision and computer graphics. Many previous methods grapple with this inherently ambiguous t…