AIBullisharXiv – CS AI · 15h ago6/10
🧠
E$^3$C: Video Generation with 3D Environmental Memory and Ego-Exo Human Pose Control
Researchers introduce E³C, a video diffusion framework enabling controllable egocentric video generation with 3D environmental memory and separate human pose controls for both camera wearers and observed subjects. The system addresses unique challenges in first-person video synthesis by maintaining scene consistency while handling rapid viewpoint changes and partial occlusions.