SymphoMotion：联合控制相机运动与物体动态的连贯视频生成
SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation
把相机位姿与物体级 3D 轨迹作为解耦条件注入视频扩散模型，为可控视频生成提供了「相机运动 vs 物体运动」分离建模的可复用范式，并配套 RealCOD-25K 真实配对数据可用于训练与评测。
原文依据 a unified motion-control framework that jointly governs camera trajectories and object dynamics within a single model
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论同时控制相机运动与物体动态对于生成连贯且富有表现力的视频至关重要，然而现有方法通常只处理其中一种运动类型，或依赖模糊的二维线索，从而将相机视差引起的运动与真实的物体运动纠缠在一起。本文提出 SymphoMotion，一个统一的运动控制框架，在单一模型内联合调控相机轨迹与物体动态。SymphoMotion 包含相机轨迹控制机制，将显式相机路径与几何感知线索相结合，以确保稳定且结构一致的视角转换；以及物体动态控制机制，将二维视觉引导与三维轨迹嵌入相结合，实现深度感知且空间连贯的物体操控。为支持大规模训练与评测，我们进一步构建了 RealCOD-25K，这是一个全面的真实世界数据集，涵盖多样化的室内外场景，包含配对的相机位姿与物体级三维轨迹，填补了统一运动控制领域的关键数据空白。大量实验与用户研究表明，SymphoMotion 在视觉保真度、相机可控性与物体运动准确性方面显著优于现有方法，为视频生成中的统一运动控制建立了新的基准。
英文原文摘要 1290 字符
Controlling both camera motion and object dynamics is essential for coherent and expressive video generation, yet current methods typically handle only one motion type or rely on ambiguous 2D cues that entangle camera-induced parallax with true object movement. We present SymphoMotion, a unified motion-control framework that jointly governs camera trajectories and object dynamics within a single model. SymphoMotion features a Camera Trajectory Control mechanism that integrates explicit camera paths with geometry-aware cues to ensure stable, structurally consistent viewpoint transitions, and an Object Dynamics Control mechanism that combines 2D visual guidance with 3D trajectory embeddings to enable depth-aware, spatially coherent object manipulation. To support large-scale training and evaluation, we further construct RealCOD-25K, a comprehensive real-world dataset containing paired camera poses and object-level 3D trajectories across diverse indoor and outdoor scenes, addressing a key data gap in unified motion control. Extensive experiments and user studies show that SymphoMotion significantly outperforms existing methods in visual fidelity, camera controllability, and object-motion accuracy, establishing a new benchmark for unified motion control in video generation.