The authors divide video controls among three physically interpretable coordinate systems.
Multi-coordinate conditioning improves camera control in generated video
The framework separates lens settings, camera and scene geometry, and object pose to control motion, framing, focus, and cinematic effects from one reference image.
Chinese Tech
Shuai Li · Jinxu Xiang · Xinyuan Li · Hanlei Guo · Xiyang Tan · Alan Zhao · +2 more
Tencent Video Solar System
Research Digest··3 min read
Li and colleagues present Gen Through the Lens, an image-to-video system designed for explicit control of camera motion, object movement, and depth of field.
Why this paper
From Tencent Video Solar System
In one line
Cross-coordinate conditioning fusion enables explicit control of camera motion, object motion, and depth-of-field in video generation.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§