🛰️ Daily AI Frontier
‹ back to 2026-07-25

GraphVid: Interactive Graph-Controllable Video Generation

Research Multimodal & Generative

Merged summary

TL;DR - GraphVid is a graph-conditioned image-to-video model that lets users control complex multi-object interactions through structured interaction graphs. It offers stronger controllability and video quality while using less training data and fewer trainable parameters than prior motion-control methods.

  • Replaces cumbersome object-trajectory drawing with semantic graph-based interaction control.
  • Introduces GraphVid-Bench, a large interaction-focused video dataset with structured relational annotations.
  • Versus Motion-I2V, reduces FID by up to 39.9% and FVD by 37.6%.
  • Improves PSNR from 9.87 to 15.98 and SSIM from 0.38 to 0.61.

Sources (1)

GraphVid: Interactive Graph-Controllable Video Generation

arXiv cs.CV Vedant Shah, Onkar Susladkar, Tushar Prakash, Kiet Nguyen, Tianjio Yu, Adheesh Juvekar, Muntasir Waheed, Ismini Lourentzou 2026-07-23 arXiv:2607.21580

TL;DR - GraphVid is a graph-conditioned image-to-video model that lets users control complex multi-object interactions through structured interaction graphs. It offers stronger controllability and video quality while using less training data and fewer trainable parameters than prior motion-control methods.

  • Replaces cumbersome object-trajectory drawing with semantic graph-based interaction control.
  • Introduces GraphVid-Bench, a large interaction-focused video dataset with structured relational annotations.
  • Versus Motion-I2V, reduces FID by up to 39.9% and FVD by 37.6%.
  • Improves PSNR from 9.87 to 15.98 and SSIM from 0.38 to 0.61.
item →