Presentation
MV-S2V: Multi-View Subject-Consistent Video Generation
SessionVideo Generation
DescriptionMV-S2V is the first work to explore video generation with multi-view subject consistency. It presents a simple yet effective framework, including a tailored data curation pipeline and a Temporally-Shifted RoPE (TS-RoPE) specially designed for multi-view reference conditioning, achieving superior 3D subject consistency w.r.t. multi-view reference images and high-quality visual outputs.
Event Type
Technical Paper
TimeMonday, 20 July 20262:00pm - 2:10pm PDT
LocationRoom 408 B
Digital Library
PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Monday, 20 July 20262:00pm - 3:30pm PDTRoom 408 B
Artificial Intelligence/Machine Learning
Generative AI
Full Conference Supporter
Full Conference
