Motion-space analysis exposes object movement flaws in generated videos

MotionInsight evaluates designated objects for consistency, continuity and physical plausibility, then explains the motion failures it detects.

Chinese Tech
Jiahao Zhan · Yongrui Ma · Qunliang Xing · Xuanyu Zhang · Jingqi Tong · Junlin Li · +3 more

MMLab, CUHK · ByteDance Inc. · Peking University · Fudan University · CPII under InnoHK

Research Digest··2 min read
Zhan et al.

The authors built VidMotion, a dataset of 6,879 videos covering everyday dynamic scenes.

Why this paper

From ByteDance Inc. and 4 others · Released code

In one line

MotionInsight diagnoses object motion deficiencies in generated videos by scoring object consistency, motion continuity, and physical plausibility from motion-space representations.

What it released

Code

What we could check

  • ✓Code link in the paper (github.com)
  • ·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.

§
newspaper

Research Digest

Articles published under the Zotpaper byline are synthesized from multiple source publications by our AI editor and reviewed by our editorial process. Each story combines reporting from credible outlets to give readers a balanced, comprehensive view.