4 papers
You Only Need One Stage: Novel-View Synthesis From A Single Blind Face Image
Taoyue Wang, Xiang Zhang, Xiaotian Li +2
We propose a novel one-stage method, NVB-Face, for generating consistent Novel-View images directly from a single Blind Face image. Existing approaches to novel-view synthesis for…
DreamWorld: Unified World Modeling in Video Generation
Boming Tan, Xiangdong Zhang, Ning Liao +5
Despite impressive progress in video generation, existing models remain limited to surface-level plausibility, lacking a coherent and unified understanding of the world. Prior appr…
Latent-Info and Low-Dimensional Learning for Human Mesh Recovery and Parallel Optimization
Xiang Zhang, Suping Wu, Sheng Yang
Existing 3D human mesh recovery methods often fail to fully exploit the latent information (e.g., human motion, shape alignment), leading to issues with limb misalignment and insuf…
Hyperbolic Space Learning Method Leveraging Temporal Motion Priors for Human Mesh Recovery
Xiang Zhang, Suping Wu, Weibin Qiu +2
3D human meshes show a natural hierarchical structure (like torso-limbs-fingers). But existing video-based 3D human mesh recovery methods usually learn mesh features in Euclidean s…