一个可快速训练的合成视频数据集，专为视频生成模型调试设计。
Dancing Stick Figures: An Introductory Dataset for Training Video Generation Models
- 64x64分辨率、64帧长的合成舞蹈骨架视频，适合单卡反复训练
- 含4020段视频，每段6秒，三视角渲染，支持16GB显存设备运行
- 每帧保留骨骼、相机、深度等标注，支持动作与拓扑精准评估
从零训练视频生成模型面临三大挑战：迭代周期长、数据难获取、评估手段粗略。为此，我们构建了Dancing Stick Figures这一合成视频数据集，以应对上述问题。该数据集包含4,020个六秒视频片段，由1,340段源动作分别从三个视角确定性渲染而成，总大小仅0.79GB，可在单台工作站GPU上高效重复训练。提供训练检查点和Colab工作流，支持在16GB Tesla T4上以较低预算复现基准训练流程。每帧保留生成状态信息，包括关节位置（ARDY cskel27）、相机参数、身体参数及源动作，并标注像素级深度、表面法向量与部件标签。这些注释支持针对可见拓扑结构和部件级运动的专用评估指标，可揭示模型对各类扰动的敏感性与盲区。
原文摘要 · Abstract (English)
Training a video-generation model from scratch is hard for reasons that precede model design. The feedback loop is long: a failure that appears only after a training run can make each attempted fix another run. The data are hard to reach: the corpora and recipes behind strong models are large, heterogeneous, and often unreleased. And scoring is blunt: open-ended generation has no single correct output, and an aggregate score does not by itself establish whether a sample succeeds or which property failed. Dancing Stick Figures is a synthetic video dataset built against these three obstacles. For iteration speed, its 64x64, 64-frame reference task is sized for practical repeated training on a single workstation GPU. For accessibility, the release is a 0.79-GB training tier of 4,020 video clips--1,340 six-second source motions, each rendered from three cameras by a deterministic dataset-generation harness--with checkpoints and a Colab workflow that reruns the reference training pipeline at reduced budget on a 16 GB Tesla T4. For scoring, every frame retains its generating state (ARDY cskel27 joint positions, camera, body parameters, and source motion) and per-pixel depth, surface normals, and part labels. These annotations support dataset-specific metrics for visible topology and part-wise motion; corruptions expose their sensitivities and blind spots.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。