LooseControlVideo:利用空间阻挡实现导演级视频控制
阅读原文· arxiv.orgLooseControlVideo通过稀疏定向3D盒子作为“阻挡”代理,使用户能创作高层级布局和轨迹,同时由视频生成模型生成真实的遮挡、动态与交互。该方法微调Wan 2.2骨干网络,并采用DNOCS编码处理3D尺寸、方向和深度顺序遮挡。在nuScenes、HO-3D和BEHAVE基准测试中,轨迹误差提升1.2倍到3倍,刚性运动一致性提升2倍,遮挡准确率提升1.5倍到2倍,显著优于现有2D盒子和流基线方法。
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.