Given a monocular video, SpaceTimePilot can independently alter the camera viewpoint and the motion sequence within the generative process, re-rendering the scene for continuous and arbitrary…
Open receipts to verify and go deeper.
About this source
Source
arXiv cs.AI
Type
Research Preprint
Published
Credibility
Peer-submitted research paper on arXiv
Always verify with the primary source before acting on this information.
arXiv cs.AI·Research Preprint·Primary Source·
SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time
TL;DR
We present SpaceTimePilot, a video diffusion model that disentangles space and time for controllable generative rendering.
Given a monocular video, SpaceTimePilot can independently alter the camera viewpoint and the motion sequence within the generative process, re-rendering the scene for continuous and arbitrary…
