DiVid introduces a diagnostic framework that breaks down video generation diversity into six interpretable dimensions: Semantic, Style, Subject, Scene, Motion, and Camera. Using off-the-shelf computer vision tools, the framework measures each dimension along with quality and faithfulness to diagnose where diversity collapses. Evaluations of representative models show that diversity is highly dimension-specific, with models that score well on global metrics still collapsing on temporal factors like Motion and Camera. Two fundamental bottlenecks are identified: default mode convergence, where models fall back to dominant patterns under open-ended prompts, and realization gaps, where explicitly requested alternatives are not faithfully realized, especially for temporal factors. This work shifts the diversity assessment from measuring whether diversity exists to diagnosing where and why it collapses, providing actionable directions for dimension-aware training and control signals.
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
In one line
Video generation models collapse diversity on specific dimensions like Motion and Camera, even when global scores are high.
Before you read this
An idea this paper builds onRead it as
The authors introduce DiVid, a framework that profiles video generation diversity along six interpretable dimensions: Semantic, Style, Subject, Scene, Motion, and Camera.
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.
How it works
before and afterThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.