Proceedings

Bootstrapping Video Interaction Generation with Synthetic State Transitions

Jiho Jang, Jin-Young Kim, Nojun Kwak, Kyungjune Baek

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 1243-1251.

https://doi.org/10.24963/ijcai.2026/139

Keywords

  • Computer Vision: Image and video synthesis and generation
  • Computer Vision: Video analysis and understanding

Abstract

While recent video generative models can synthesize high-fidelity videos, they struggle to portray plausible physical interactions and the resulting state transitions, a critical bottleneck for applications in robotics and VR/AR. To address this, we introduce a framework to generate a scalable synthetic dataset of controllable interactions.

Our pipeline leverages a structured taxonomy and state-of-the-art image editing models to create explicit `start' and `end' state images, which serve as visual anchors for the interaction. To generate a seamless video utilizing these anchors, we propose State-Guided Sampling (SGS), a novel sampling technique that mitigates artifacts common in naive conditional generation. Furthermore, we develop and validate a new automated evaluation system that aligns with human judgments to ensure data quality.

Experiments show that fine-tuning a base model on our dataset significantly enhances its ability to generate plausible interactions.

Jiho Jang, Jin-Young Kim, Nojun Kwak, and Kyungjune Baek. 2026. Bootstrapping Video Interaction Generation with Synthetic State Transitions. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 1243–1251. https://doi.org/10.24963/ijcai.2026/139
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards