Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts
This dataset addresses a gap for researchers in computer vision and robotics working on shape repair, though it is incremental as it builds on existing synthetic datasets.
The authors tackled the lack of real-world damaged geometry datasets for automated shape repair by introducing Fantastic Breaks, a dataset of 150 paired 3D scans of broken and complete objects, which revealed differences from synthetic datasets and enabled experimental evaluation of learning-based repair methods.
Automated shape repair approaches currently lack access to datasets that describe real-world damaged geometry. We present Fantastic Breaks (and Where to Find Them: https://terascale-all-sensing-research-studio.github.io/FantasticBreaks), 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, proxy 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 synthetic fracture datasets generated using geometric and physics-based methods. We show experimental shape repair evaluation with Fantastic Breaks using multiple learning-based approaches pre-trained with synthetic datasets and re-trained with subset of Fantastic Breaks.