The authors developed DiVid, a dimension-level diagnostic framework that measures video generation diversity along six complementary axes: Semantic, Style, Subject, Scene, Motion, and Camera.
Diagnosing where video models collapse diversity across dimensions
DiVid decomposes video generation diversity into six interpretable axes and reveals that models collapse most severely on temporal factors like motion and camera.
Chinese Tech
Huanran Hu · Zihui Ren · Dingyi Yang · Zhinan Song · Guozheng Wu · Tiezheng Ge · +1 more
Renmin University of China · Alibaba Group · Tianjin University
Research Digest··3 min read
The authors introduce DiVid, a framework that profiles video generation diversity along six interpretable dimensions: Semantic, Style, Subject, Scene, Motion, and Camera.
Why this paper
From Alibaba Group and 2 others
In one line
Video generation models collapse diversity on specific dimensions like Motion and Camera, even when global scores are high.
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.
§