Fantastic Breaks

A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts

CVPR 2023

Nikolas Lamb, Cameron Palmer, Ben Molloy, Sean Banerjee, Natasha Kholgade Banerjee,

Terascale All-sensing Research Studio (TARS) at Clarkson University, USA

paper icon arXiv drive icon Data


Abstract

Automated shape repair approaches currently lack access to datasets that describe real-world damage geometry. We present Fantastic Breaks (And Where to Find Them), a dataset containing scanned, waterproofed, and cleaned 3D meshes for 150 broken objects, paired and geometrically aligned with complete counterparts. Fantastic Breaks contains class and material labels, synthetic proxies of repair parts that join to broken meshes to generate complete meshes, and manually annotated fracture boundaries. Through a detailed analysis of fracture geometry, we reveal differences between Fantastic Breaks and datasets of synthetically fractured objects generated using geometric and physics-based methods. We show experimental results of shape repair with Fantastic Breaks using multiple learning-based approaches pre-trained using a synthetic dataset and re-trained using a subset of Fantastic Breaks.

Object Demo


Citation

                    

    @inproceedings{lamb2023fantastic,
        title={Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts},
        author={Lamb, Nikolas and Palmer, Cameron and Molloy, Ben and Banerjee, Sean and Banerjee, Natasha Kholgade},
        booktitle={Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
        year={2023}
    }