Research map / 3D vision / Face and shape
Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Retrain with Fantastic Breaks after Geometric Breaks pretraining | DeepMend · Fantastic Breaks test | CD: 0.059 -> 0.051 | Helped |
| Retrain with Fantastic Breaks after Geometric Breaks pretraining | DeepJoin · Fantastic Breaks test | CD: 0.030 -> 0.022 | Helped |
| Retrain with Fantastic Breaks after Geometric Breaks pretraining | MendNet · Fantastic Breaks test | CD: 0.080 -> 0.094 | Hurt |
| Retrain with Fantastic Breaks after Breaking Bad pretraining | MendNet · Fantastic Breaks test | CD: 0.110 -> 0.116 | Hurt |
| Retrain with Fantastic Breaks after Breaking Bad pretraining | DeepMend · Fantastic Breaks test | CD: 0.065 -> 0.092 | Hurt |
| Retrain with Fantastic Breaks after Breaking Bad pretraining | DeepJoin · Fantastic Breaks test | CD: 0.061 -> 0.076 | Hurt |
| Use Breaking Bad rather than Geometric Breaks for pretraining | MendNet, DeepMend, and DeepJoin · Fantastic Breaks test | CD: 0.080 and 0.110; 0.059 and 0.065; 0.030 and 0.061 | Hurt |
| Use real-world fractured meshes rather than synthetic fractured meshes | Fantastic Breaks dataset · Broken meshes | 75th percentile convexity: 0.519; 0.828; 0.746 | Mixed |
Closest papers by meaning
- Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving (NeurIPS 2024 · similarity 0.86)
- PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify (ICLR 2025 · similarity 0.83)
- Scalable Geometric Fracture Assembly via Co-creation Space among Assemblers (AAAI 2024 · similarity 0.83)
- Physically Compatible 3D Object Modeling from a Single Image (NeurIPS 2024 · similarity 0.82)
- Cracks in the Foundation: A Civil Infrastructure Dataset to Challenge Vision Foundation Models (NeurIPS 2026 · similarity 0.82)
- MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds (NeurIPS 2025 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.