Presentation
ViSA: Physics-based Virtual Stunt Actors for Ballistic Stunts
DescriptionWe introduce ViSA (Virtual Stunt Actors), an interactive animation system using deep reinforcement learning to generate realistic ballistic stunt actions. It efficiently produces dynamic scenes commonly seen in films and TV dramas, such as traffic accidents and stairway falls. A novel action space design enables scene generation within minutes.
Event Type
Technical Paper
TimeWednesday, 13 August 20254:25pm - 4:35pm PDT
LocationWest Building, Rooms 220-222
ACM Digital Library
Journal Papers' PDFs
Conference Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Wednesday, 13 August 20253:45pm - 5:35pm PDTWest Building, Rooms 220-222
Research & Education
Livestreamed
Recorded
Full Conference
Virtual Access
Wednesday
