SceneShifter introduces training-free multi-scene temporal control for audio-driven human animation
A new arXiv paper, SceneShifter, proposes a training-free method for multi-scene temporal control in audio-driven human animation, orchestrating backgrounds and temporal transitions.
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-11-10 05:00 · arXiv cs.CV
SceneShifter: Training-free Multi-Scene Temporal Control for Audio-driven Human Animation