The authors introduce AVE, a two-stage video editing framework.
Decomposing video editing into keyframe editing and motion-guided interpolation
A two-stage framework transforms powerful image editors into video editors without expensive end-to-end training
Chinese Tech
Feng Wang · Zijie Li · Ceyuan Yang · Alan Yuille · Peng Wang
ByteDance Seed · Johns Hopkins University
Research Digest··2 min read
The authors propose AVE, which first edits a sparse set of keyframes using a strong image editor, then generates the full video via motion-guided image-to-video diffusion, treating edited keyframes as anchors.
Why this paper
From ByteDance Seed and Johns Hopkins University
In one line
Video editing is achieved by editing sparse keyframes with an image editor and interpolating with motion-guided video diffusion.
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.
§