GraphVid: Interactive Graph-Controllable Video Generation

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Vedant Shah, Onkar Susladkar, Tushar Prakash, Kiet Nguyen, Tianjio Yu, Adheesh Juvekar, Muntasir Waheed, Ismini Lourentzou
• Venue: arXiv: cs.CV
• Published: 2026-07-23
• Collected: 2026-07-24
• URL: http://arxiv.org/abs/2607.21580v1
• PDF: https://arxiv.org/pdf/2607.21580v1
• DOI: UNKNOWN

Plain-Language Brief

The researchers introduce GraphVid, a model that generates interactive videos using structured interaction graphs, allowing for flexible and precise control. The model shows strong performance compared to Motion-I2V in terms of FID, FVD, PSNR, and SSIM, requiring less training data and fewer trainable parameters.

What the Document Says

• Researchers introduced a graph-conditioned image-to-video generation model called GraphVid.
• GraphVid enables interactive control through structured interaction graphs.
• A large-scale interaction-centric video dataset, GraphVid-Bench, was curated for training interaction-aware video generation models.
• GraphVid delivers strong controllability and video quality compared to Motion-I2V.
• GraphVid reduces FID by up to 39.9% and FVD by 37.6% compared to Motion-I2V.
• PSNR increased from 9.87 to 15.98, and SSIM increased from 0.38 to 0.61 for GraphVid compared to Motion-I2V.

Key Concepts Mentioned

• GraphVid
• interactive control
• structured interaction graphs
• video generation
• GraphVid-Bench
• Motion-I2V
• FID
• FVD
• PSNR
• SSIM

Claims Made by the Document

• GraphVid provides strong controllability and video quality.
• GraphVid outperforms Motion-I2V in terms of FID, FVD, PSNR, and SSIM.

Evidence Used

• Reduction in FID by up to 39.9% and FVD by 37.6% compared to Motion-I2V.
• Increase in PSNR from 9.87 to 15.98, and SSIM from 0.38 to 0.61 for GraphVid compared to Motion-I2V.

Methods / Approach

• Graph-conditioned image-to-video generation
• Use of structured interaction graphs
• Training on the GraphVid-Bench dataset

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

The study does not discuss any limitations or potential pitfalls of the proposed approach.

Open Questions

• What are the specifics of the GraphVid model architecture?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The text does not provide details about the GraphVid model's architecture.

Raw Abstract / Excerpt

Controllable video generation remains challenging due to the difficulty of specifying precise multi-object interactions using text prompts or motion-control inputs that primarily constrain pixel movement. In practice, trajectory-based control often requires users to draw accurate tracks for multiple objects, which scales poorly with scene complexity and becomes ambiguous under occlusion or overlap. To enable flexible yet precise multi-subject control, we introduce $\textbf{GraphVid}$, a graph-conditioned image-to-video generation model that enables interactive control through structured interaction graphs. We further curate $\textbf{GraphVid-Bench}$, a large-scale interaction-centric video dataset with structured relational annotations to enable training of interaction-aware video generation models. Despite using substantially less training data and fewer trainable parameters than prior motion-control methods, GraphVid delivers strong controllability and video quality. Compared with Motion-I2V, GraphVid reduces FID by up to 39.9% and FVD by 37.6%, while improving PSNR (9.87=>15.98) and SSIM (0.38=>0.61). Our results highlight the potential of structured semantic interfaces as a powerful paradigm for controllable video generation.