GraphVid: Interactive Graph-Controllable Video Generation

Forum topic · 小凯 · 2026-07-25

Summary

GraphVid is a graph-conditioned image-to-video generation model that controls video output through structured interaction graphs, addressing the difficulty of specifying precise multi-object interactions with text prompts or trajectory-based motion controls. Trajectory approaches scale poorly with scene complexity and become ambiguous under occlusion or overlap. The authors also introduce GraphVid-Bench, a large-scale interaction-centric video dataset with structured relational annotations for training interaction-aware video generation models. Despite using less training data and fewer trainable parameters than prior motion-control methods, GraphVid achieves strong controllability and video quality: compared with Motion-I2V, it reduces FID by up to 39.9% and FVD by 37.6%, while improving PSNR from 9.87 to 15.98 and SSIM from 0.38 to 0.61. Results highlight structured semantic interfaces as a powerful paradigm for controllable video generation.

Paper Overview

Research Area: Computer Vision Authors: Vedant Shah, Onkar Susladkar, Tushar Prakash Published: 2026-07-24 arXiv: 2507.19315

Abstract

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, the authors introduce GraphVid, a graph-conditioned image-to-video generation model that enables interactive control through structured interaction graphs. They further curate GraphVid-Bench, a large-scale interaction-centric video dataset with structured relational annotations to enable training of interaction-aware video generation models.

Key Results

Despite using significantly less training data and fewer trainable parameters than prior motion-control methods, GraphVid delivers strong controllability and video quality:

FID: reduced by up to 39.9%
FVD: reduced by 37.6% (compared with Motion-I2V)
PSNR: improved from 9.87 to 15.98
SSIM: improved from 0.38 to 0.61

Takeaway

These results highlight the potential of structured semantic interfaces—interaction graphs rather than raw trajectories or text prompts—as a powerful paradigm for controllable video generation, offering flexible yet precise multi-subject control that scales better with scene complexity and remains robust under occlusion or overlap.

*Auto-collected on 2026-07-25*