| title | LooseControlVideo: Directorial Video Control using Spatial Blocking |
|---|---|
| authors | Shariq Farooq Bhat, Niloy J. Mitra, Kalyan Sunkavalli |
| date | 2026-06-17 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.19495 |
| affiliation | Adobe |
| upvotes | 7 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Precise 3D spatial orchestration in text-to-video generation remains a significant challenge, particularly for multi-object scenes where semantic layout and temporal dynamics are often entangled. While existing depth-conditioned models achieve good structural fidelity, they necessitate dense, frame-accurate guidance that is labor-intensive to author for dynamic events involving deformable objects. We present LooseControlVideo, a framework that enables intuitive and expressive control by using sparse, oriented 3D boxes as a "blocking" proxy. This allows users to author high-level layout and trajectory while leveraging a video generative model to generate realistic occlusions, dynamics and interactions. We achieve this by fine-tuning a Wan 2.2 backbone on a video dataset annotated with DNOCS, a novel encoding for 3D size, orientation and depth-ordered occlusions. Furthermore, our method allows for localized refinement, such as adjusting a jump trajectory or adding an interaction, with minimal disruption to the global scene context. Extensive evaluations on the nuScenes, HO-3D, and BEHAVE benchmarks demonstrate that LooseControlVideo significantly outperforms existing 2D-box and flow-based baselines. Our findings indicate a 1.2x to 3x improvement in Trajectory Error; 2x improvement in Rigid Motion Consistency; and a 1.5x to 2x increase in Occlusion Accuracy over current state-of-the-art layout-conditioned models, demonstrating that oriented 3D primitives provide good geometric prior for complex, multi-agent video authoring. |
cite
@misc{bhat2026loosecontrolvideo,
title={LooseControlVideo: Directorial Video Control using Spatial Blocking},
author={Shariq Farooq Bhat and Niloy J. Mitra and Kalyan Sunkavalli},
year={2026},
eprint={2606.19495},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.19495}
}