Breaking Bad: A Dataset for Geometric Fracture and Reassembly

Under Review at NeurIPS 2022 Datasets and Benchmarks Track

Silvia Sellán1,*Yun-Chun Chen1,2,*Ziyi Wu1,2,*Animesh Garg1,2,3Alec Jacobson1,2,4
1University of Toronto   2Vector Institute   3NVIDIA   4Adobe Research, Toronto  
* Equal contribution


Our Breaking Bad Dataset contains around 10k meshes from PartNet and Thingi10k. For each mesh, we pre-compute 20 fracture modes and then simulate 80 fractures from them, resulting in a total of 1,047,400 breakdown patterns. We divide our dataset into three subsets, namely, everyday, artifact and other to faciliate different applications.

Accessing the dataset

See README for detailed instructions.


Our dataset is divided into three categories: