Timezone: »

Breaking Bad: A Dataset for Geometric Fracture and Reassembly
Silvia Sellán · Yun-Chun Chen · Ziyi Wu · Animesh Garg · Alec Jacobson

Tue Nov 29 09:00 AM -- 11:00 AM (PST) @ Hall J #1024

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 Information

Silvia Sellán (Department of Computer Science, University of Toronto)
Yun-Chun Chen (University of Toronto Adobe Research)
Ziyi Wu (University of Toronto)
Ziyi Wu

Ziyi Wu received a B.Eng. degree in the Department of Automation from Tsinghua University in 2021. He is a second year PhD student at the University of Toronto supervised by Prof. Igor Gilitschenski. His research interests include 3D vision, object-centric learning, and robotics.

Animesh Garg (Georgia Institute of Technology)
Alec Jacobson (University of Toronto)

More from the Same Authors