Breaking Bad: A Dataset for Geometric Fracture and Reassembly

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

Abstract: 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/.

Author Statement: Yes

URL: https://breaking-bad-dataset.github.io/

Dataset Url:

URL: https://breaking-bad-dataset.github.io/
Please see the instructions on the website.

License:

Code: MIT license.
Dataset: We gather our base models following the licenses specified in each of the source datasets: the MIT license in the PartNet dataset and a variety of open-source licenses in the Thingi10K dataset (see Figure 12 in [65]). We release each model in our dataset with an as-permissive-as-possible license compatible with its underlying base model.

Contribution Process Agreement: Yes

In Person Attendance: Yes

Community Implementations: [ 3 code implementations](https://www.catalyzex.com/paper/arxiv:2210.11463/code)