构建首个真实物体密度场数据集，助力机器人物理理解与仿真。
XDen-1K: A Density Field Dataset of Real-World Objects
- 基于双平面X光扫描重建1000个真实物体的体密度场。
- 提供高精度3D模型与部件标注，支持密度估计与分割任务。
- 适用于机器人抓取、物理仿真等具身智能研究。
深刻理解物理世界对机器人操作和真实物理模拟至关重要。当前基于视觉语言模型及其他学习方法虽在物理属性推断上展现潜力，但评估常受限于缺乏物理基准数据。为此，我们提出XDen-1K，首个大规模多模态数据集，为真实物体提供物理一致的密度场。XDen-1K包含1000个真实物体，覆盖137类，每件物体均配有高分辨率、经精心校准的3D几何模型（含部件级标注）及对应的双平面真实X光扫描。此外，通过新型优化框架，从稀疏双平面X光视图中重建出高保真体密度场。该数据集还提供了密度估计基准，并支持基于X光条件的体分割任务。实验表明，由XDen-1K导出的质心先验可提升机器人操作性能。通过提供真实世界X光扫描与物理一致性密度场，XDen-1K为推进物理属性推断与具身人工智能奠定了基础。
原文摘要 · Abstract (English)
A deep understanding of the physical world is essential for robotic manipulation and physically realistic simulation. While current methods, including VLM-based and other learning-based approaches, have shown promise in physical property inference, their evaluation is often hindered by the lack of physically grounded reference data. To address this gap, we introduce XDen-1K, the first large-scale multimodal dataset that provides physically grounded density field for real-world objects. XDen-1K comprises 1,000 real-world objects spanning 137 categories, with comprehensive data for each object, including a high-resolution, carefully curated 3D geometric model with part-level annotations and paired real-world biplanar X-ray scans. In addition, XDen-1K includes high-fidelity volumetric density field reconstructed from sparse biplanar X-ray views via a novel optimization framework. XDen-1K also provides a benchmark for density estimation and enables X-ray-conditioned volumetric segmentation. Experiments further demonstrate that the center-of-mass prior derived by XDen-1K can improve robotic manipulation performance. By providing real-world X-ray scans and physics-consistent density field, XDen-1K establishes a foundation for advancing physical property inference and embodied AI.
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。