重新思考具身世界的视频生成模型
Rethinking Video Generation Model for the Embodied World
AI总结：
本文提出Rbench机器人视频生成基准和RoVid-X数据集，旨在解决高保真机器人视频生成中的数据短缺问题，推动具身AI发展。
摘要：
视频生成模型在提升具身智能方面取得了显著进展，解锁了生成多样化机器人数据的新可能性，这些数据能够捕捉物理世界中的感知、推理和行动。然而，合成高质量视频以准确反映真实世界的机器人交互仍具挑战性，缺乏标准化基准限制了公平比较和进步。为解决这一差距，我们引入了一个全面的机器人基准，Rbench，旨在评估面向机器人视频生成的五个任务领域和四种不同的具身形式。它通过可重复的子指标，包括结构性一致性、物理合理性以及动作完整性，评估任务层面的正确性和视觉保真度。对25个代表性模型的评估突显了在生成物理真实机器人行为方面的显著缺陷。此外，该基准与人类评估的斯皮尔曼相关系数达到0.96，验证了其有效性。虽然Rbench提供了识别这些缺陷的必要视角，但实现物理真实性需要超越评估，解决高质量训练数据的关键短缺。受这些见解的驱动，我们引入了一个改进的四阶段数据管道，产生RoVid-X，最大的开源机器人视频生成数据集，包含400万段标注视频片段，涵盖数千个任务，并补充了全面的物理属性注释。集体而言，这一评估与数据的协同生态系统为视频模型的严格评估和可扩展训练奠定了坚实基础，加速了具身AI向通用智能的演变。
英文摘要：
Video generation models have significantly advanced embodied intelligence, unlocking new possibilities for generating diverse robot data that capture perception, reasoning, and action in the physical world. However, synthesizing high-quality videos that accurately reflect real-world robotic interactions remains challenging, and the lack of a standardized benchmark limits fair comparisons and progress. To address this gap, we introduce a comprehensive robotics benchmark, RBench, designed to evaluate robot-oriented video generation across five task domains and four distinct embodiments. It assesses both task-level correctness and visual fidelity through reproducible sub-metrics, including structural consistency, physical plausibility, and action completeness. Evaluation of 25 representative models highlights significant deficiencies in generating physically realistic robot behaviors. Furthermore, the benchmark achieves a Spearman correlation coefficient of 0.96 with human evaluations, validating its effectiveness. While RBench provides the necessary lens to identify these deficiencies, achieving physical realism requires moving beyond evaluation to address the critical shortage of high-quality training data. Driven by these insights, we introduce a refined four-stage data pipeline, resulting in RoVid-X, the largest open-source robotic dataset for video generation with 4 million annotated video clips, covering thousands of tasks and enriched with comprehensive physical property annotations. Collectively, this synergistic ecosystem of evaluation and data establishes a robust foundation for rigorous assessment and scalable training of video models, accelerating the evolution of embodied AI toward general intelligence.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
