arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.14152cs.CV
收藏

Fantastic Breaks:真实世界破损物体及其完整对应物的配对3D扫描数据集

Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts

Clarkson University(克拉克森大学)

Nikolas Lamb, Cameron Palmer, Benjamin Molloy, Sean Banerjee, Natasha Kholgade Banerjee

AI总结:

针对现有形状修复方法缺乏真实破损几何数据集的问题,研究者提出包含150组配对真实破损与完整3D扫描的Fantastic Breaks数据集,分析了其与合成断裂数据集的差异,并验证了其用于模型重训练提升修复效果的价值。

摘要:

当前的自动化形状修复方法缺乏描述真实世界破损几何结构的数据集。我们推出Fantastic Breaks(以及在哪里找到它们:https://terascale-all-sensing-research-studio.github.io/FantasticBreaks),该数据集包含150个破损物体的经扫描、防水处理和清理的3D网格,且与完整对应物配对并实现几何对齐。Fantastic Breaks包含类别与材质标签、可与破损网格拼接以生成完整网格的代理修复部件,以及人工标注的断裂边界。通过对断裂几何结构的详细分析,我们揭示了Fantastic Breaks与采用几何和基于物理的方法生成的合成断裂数据集之间的差异。我们使用多种基于学习的方法在Fantastic Breaks上开展了形状修复实验评估,这些方法先在合成数据集上预训练,再用Fantastic Breaks的子集重新训练。

英文摘要:

Automated shape repair approaches currently lack access to datasets that describe real-world damaged geometry. We present Fantastic Breaks (and Where to Find Them: https://terascale-all-sensing-research-studio.github.io/FantasticBreaks), a dataset containing scanned, waterproofed, and cleaned 3D meshes for 150 broken objects, paired and geometrically aligned with complete counterparts. Fantastic Breaks contains class and material labels, proxy repair parts that join to broken meshes to generate complete meshes, and manually annotated fracture boundaries. Through a detailed analysis of fracture geometry, we reveal differences between Fantastic Breaks and synthetic fracture datasets generated using geometric and physics-based methods. We show experimental shape repair evaluation with Fantastic Breaks using multiple learning-based approaches pre-trained with synthetic datasets and re-trained with subset of Fantastic Breaks.

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。

↑