A Study of the Design Space of Motion and Disocclusion Control in Video Generation

arXiv:2512.13392v3 Announce Type: replace Abstract: Disocclusion occurs when object movement reveals previously hidden content. Existing image-to-video methods provide different forms of motion and disocclusion control, yet the design space they span remains poorly understood. In this work, we systematically explore an algorithmic design space spanning motion specification (text-based versus tracking-based) and disocclusion specification (text-based versus image-based). To facilitate this study, we construct a benchmark consisting of both synthetic scenes and captured scenes, covering rigid and deformable motions, as well as static and dynamic disoccluded objects. We compare existing and adapted methods across this design space to analyze the strengths and limitations of different control strategies for handling disocclusions during motion. Our study reveals that tracking-based guidance improves motion accuracy, while image-based guidance improves the fidelity of newly revealed content. However, jointly controlling the appearance and dynamics of disoccluded objects remains a challenging open problem, particularly in scenarios where newly revealed objects undergo their own motion after becoming visible.

Related

• SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation
• VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning
• Holo-World: Unified Camera, Object and Weather Control for Video World Model
• CatalogStitch: Dimension-Aware and Occlusion-Preserving Object Compositing for Catalog Image Generation

Source: arXiv cs.CV | 2026-09-01