SceneScribe-1M：一个具有全面几何与语义标注的大规模视频数据集
SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations
该数据集同时提供相机参数、稠密深度与一致 3D 点轨迹，可直接用于训练单目深度估计、动态点跟踪与相机可控视频生成模型，并为几何感知的视频生成提供统一的监督信号与评测基准。
原文依据 each meticulously annotated with detailed textual descriptions, precise camera parameters, dense depth maps, and consistent 3D point tracks
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论三维几何感知与视频合成的融合，对同时富含语义信息与时空信息的大规模视频数据产生了前所未有的需求。现有数据集或推动了三维理解，或推动了视频生成，但在提供一个可规模化支撑这两个领域的统一资源方面仍存在显著空白。为弥合这一鸿沟，我们提出 SceneScribe-1M，一个新的大规模多模态视频数据集。它包含一百万段真实场景视频，每段视频都经过细致标注，配有详细的文本描述、精确的相机参数、稠密深度图以及一致的 3D 点轨迹。我们通过在一系列广泛的下游任务上建立基准，展示了 SceneScribe-1M 的通用性与价值，这些任务包括单目深度估计、场景重建和动态点跟踪，以及诸如文本到视频合成（无论是否带相机控制）之类的生成任务。通过开源 SceneScribe-1M，我们希望提供一个全面的基准与研究催化剂，推动既能感知动态三维世界、又能生成可控且逼真视频内容的模型的发展。
英文原文摘要 1195 字符
The convergence of 3D geometric perception and video synthesis has created an unprecedented demand for large-scale video data that is rich in both semantic and spatio-temporal information. While existing datasets have advanced either 3D understanding or video generation, a significant gap remains in providing a unified resource that supports both domains at scale. To bridge this chasm, we introduce SceneScribe-1M, a new large-scale, multi-modal video dataset. It comprises one million in-the-wild videos, each meticulously annotated with detailed textual descriptions, precise camera parameters, dense depth maps, and consistent 3D point tracks. We demonstrate the versatility and value of SceneScribe-1M by establishing benchmarks across a wide array of downstream tasks, including monocular depth estimation, scene reconstruction, and dynamic point tracking, as well as generative tasks such as text-to-video synthesis, with or without camera control. By open-sourcing SceneScribe-1M, we aim to provide a comprehensive benchmark and a catalyst for research, fostering the development of models that can both perceive the dynamic 3D world and generate controllable, realistic video content.