Presentation

UCM: Unified Modeling of Camera Control and Memory with Time-aware Positional Encoding Warping for World Models
DescriptionWe propose UCM, a novel framework for the unified modeling of long-term scene consistency and camera controllability in video generation-based world models. Trained on over 500K monocular videos, UCM achieves high-fidelity world exploration capability with excellent generalizability to open-world environments.
Event Type
Technical Paper
TimeTuesday, 21 July 20269:40am - 9:50am PDT
LocationRoom 408 B
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Tuesday, 21 July 20269:00am - 10:30am PDTRoom 408 B
Keywords
Generative AI
Registration Categories
Full Conference Supporter
Full Conference