Human4K提供600万张4K多视角图像，提升全身3D人体重建精度。
Human4K: A Large-Scale 4K Multi-View Mocap Dataset for Whole-Body 3D Human Reconstruction
- 八视角4K高清摄像同步采集，配合Vicon动作捕捉系统
- 覆盖11人复杂动作，含大量肢体遮挡与深度模糊场景
- 显著提升手部、足部及遮挡部位重建效果，适合高精度应用
近期3D人体重建技术虽有进步，但在真实世界复杂场景中仍存在几何不稳定、关节错位和深度模糊下的预测不可靠问题。主要原因在于现有数据集缺乏高分辨率图像、高精度标注与多样全身动作的结合。为此，我们提出Human4K，一个大规模4K多视角全身人体重建数据集，包含超过六百万张4K图像，由八视角高分辨率相机系统同步采集，并与专业Vicon动作捕捉系统对齐。数据涵盖11名受试者执行复杂、高度关节化且强自遮挡的全身动作。所有序列通过运动重定向与精修模块（MRRM）处理，确保全身及四肢的精确对齐。实验表明，使用Human4K训练可稳定提升标准基准上的全身重建性能，尤其在手部、足部及深度模糊的肢体配置上提升显著。
原文摘要 · Abstract (English)
Recent advances in 3D human reconstruction have improved overall performance, yet current models still fail in the most challenging real-world scenarios. They often produce unstable geometry, inaccurate limb articulation and unreliable predictions under depth ambiguity or self-occlusion. A key reason is that existing datasets still lack the combination of high-resolution images, high-precision annotations and diverse whole-body motions required to support robust reconstruction. To address this gap, we present Human4K, a large-scale 4K multi-view whole-body human reconstruction dataset with mocap-accurate SMPL-X annotations. Human4K contains over six million 4K images captured by an eight-view high-resolution camera system synchronized with a professional Vicon motion capture setup, covering 11 subjects performing complex, highly articulated and strongly self-occluded full-body motions. All sequences are processed by a Motion-Retargeting and Refinement Module (MRRM) to ensure precise alignment for the full body and extremities. Experimental results show that training with Human4K consistently improves whole-body reconstruction on standard benchmarks, with particularly large gains for hands, feet and depth-ambiguous limb configurations.
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。