A camera-controlled video world model must keep a scene consistent when the camera returns to it. Memories that render stored features into the target frame can turn depth and pose errors into ghosting or duplicated structure. Positional transport avoids that resampling by relocating a historical patch's address rather...
Zhu-Feng Xu, Heng-Lei Lv, Bai-Lin Deng et al.· 0 citations
MeshSeqGen is introduced, a zero-shot framework that simplifies this process by using the motions from generated video frames to guide mesh deformation, and its mesh-based Gaussian representation ensures the final animations are both plausible and structurally consistent.
Yun-Peng Xiao, Jie Yang, Chuan Li et al.· IEEE Transactions on Visuali...· 0 citations
FLASHand is proposed, the first feed-forward relightable and animatable 3D hand reconstruction model from a single RGB image, and introduces a mesh-based disentangled 2D Gaussian splatting hand representation to ensure plausible geometry generation and achieve high-fidelity animation and relighting.
Ling-Xiao Zhang, Lin Gao, Wei-Hong He et al.· International Conference on...· 0 citations
This work proposes CameraSquad, a multi-trajectory camera control framework that supports both single-trajectory and parallel multi-trajectory generation, and designs a dual-mode cross-view attention mechanism that maintains consistency across parallel trajectories while guaranteeing camera control precision.
Zhufeng Xu, Xuan Gao, Bailin Deng et al.· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
