English

Contrastive Sequential-Diffusion Learning: Non-linear and Multi-Scene Instructional Video Synthesis

Computer Vision and Pattern Recognition 2024-12-10 v3

Abstract

Generated video scenes for action-centric sequence descriptions, such as recipe instructions and do-it-yourself projects, often include non-linear patterns, where the next video may need to be visually consistent not with the immediately preceding video but with earlier ones. Current multi-scene video synthesis approaches fail to meet these consistency requirements. To address this, we propose a contrastive sequential video diffusion method that selects the most suitable previously generated scene to guide and condition the denoising process of the next scene. The result is a multi-scene video that is grounded in the scene descriptions and coherent w.r.t. the scenes that require visual consistency. Experiments with action-centered data from the real world demonstrate the practicality and improved consistency of our model compared to previous work.

Keywords

Cite

@article{arxiv.2407.11814,
  title  = {Contrastive Sequential-Diffusion Learning: Non-linear and Multi-Scene Instructional Video Synthesis},
  author = {Vasco Ramos and Yonatan Bitton and Michal Yarom and Idan Szpektor and Joao Magalhaes},
  journal= {arXiv preprint arXiv:2407.11814},
  year   = {2024}
}
R2 v1 2026-06-28T17:43:12.439Z