We provide additional details and results to complement the main paper. Fracture reassembly is an important task in the real world, e.g. We believe this research benefits both the economy and society. Even with advanced learning methods, human trust in AI is still a problem. Figure 6 shows the architecture of the three baseline methods, i.e., Global, LSTM and DGL. Then, we concatenate the global feature with each part feature and apply a shared-weight MLP network to regress the SE(3) pose for each input point cloud.

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/.