FreeOrbit4D: Training-Free Arbitrary Camera Trajectory Retargeting for Video
jiqizhixin · x · 2026-07-05
Researchers from UIUC, UPenn, and Eyeline Labs introduced FreeOrbit4D, a training-free method to retarget monocular video to any new camera path, including bullet-time orbits. It works by separating foreground and background, using multi-view diffusion to complete unseen areas for full 4D scene reconstruction, and projecting geometry into the target camera view via depth and visibility guidance. The results are more faithful and temporally consistent under extreme angle changes, outperforming previous diffusion-based methods.
More from Multimodal
- TischEins, a large Midjourney SREF library, relaunches with new design after security outage — tisch_eins · 2026-10-26
- MOSS-Image-SFT 4-step distillation tops 16.5K downloads on Hugging Face — _akhaliq · 2026-10-26
- Claude Code can now edit videos: a 10-prompt workflow from raw footage to final cut — TawohAwa · 2026-10-26
- One-sentence 3D worlds turn cinematic with CineMap and TapNow — gizakdag · 2026-10-26
- No Camera Needed: Creator Builds an Entire World in CineMap and Directs It Into Cinema — gizakdag · 2026-10-26
- Kling vs. Seedance: the Chinese AI video model rivalry — DavidmComfort · 2026-10-26