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 2210.11463cs.CVcs.GRcs.LGcs.RO
收藏

Breaking Bad:几何断裂和重组数据集

Breaking Bad: A Dataset for Geometric Fracture and Reassembly

University of Toronto(多伦多大学);Vector Institute(向量研究所);NVIDIA(英伟达);Adobe Research(Adobe研究院)

Silvia Sellán, Yun-Chun Chen, Ziyi Wu, Animesh Garg, Alec Jacobson

摘要:

我们介绍Breaking Bad,一个大规模的断裂对象数据集。我们的数据集由一万个基本模型模拟的超过一百万个断裂对象组成。断裂模拟由最近的基于物理的算法提供动力,该算法有效地生成对象的各种断裂模式。现有的形状装配数据集根据语义上有意义的部分分解对象,有效地建模的建设过程。相反,《绝命毒师》模拟了几何对象如何自然地分裂成碎片的破坏过程。我们的数据集作为一个基准,使断裂的对象重组的研究,并提出了新的挑战,几何形状的理解。我们用几个几何测量来分析我们的数据集,并在各种设置下对三种最先进的形状组装深度学习方法进行基准测试。广泛的实验结果表明,我们的数据集的难度,呼吁未来的研究,专门为几何形状的组装任务的模型设计。我们将数据集托管在https://breaking-bad-dataset.github.io/。

英文摘要:

We introduce Breaking Bad, a large-scale dataset of fractured objects. Our dataset consists of over one million fractured objects simulated from ten thousand base models. The fracture simulation is powered by a recent physically based algorithm that efficiently generates a variety of fracture modes of an object. Existing shape assembly datasets decompose objects according to semantically meaningful parts, effectively modeling the construction process. In contrast, Breaking Bad models the destruction process of how a geometric object naturally breaks into fragments. Our dataset serves as a benchmark that enables the study of fractured object reassembly and presents new challenges for geometric shape understanding. We analyze our dataset with several geometry measurements and benchmark three state-of-the-art shape assembly deep learning methods under various settings. Extensive experimental results demonstrate the difficulty of our dataset, calling on future research in model designs specifically for the geometric shape assembly task. We host our dataset at https://breaking-bad-dataset.github.io/.

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。

↑