Qu et al.
Image-based visual examples enable powerful video editing without large paired video datasets
The VINCIE-NExT framework breaks video editing into an image-to-image step followed by image-to-video synthesis, using the edited image as a blueprint for all frames, achieving state-of-the-art results on a benchmark.
Chinese Tech
Leigang Qu · Feng Cheng · Ziyan Yang · Bangbang Yang · Zhaoyang Huang · Wei Chow · +4 more
National University of Singapore · ByteDance Seed · University of Science and Technology of China
Research Digest··3 min read
The authors propose VINCIE-NExT, a video editing framework that leverages in-context visual demonstrations from image editing pairs to guide video edits.
Why this paper
From ByteDance Seed and 2 others
In one line
Video editing can be achieved by routing edits through the image domain with an in-context visual demonstration, reducing the need for expensive paired video data.
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.
§