mlsanityData to 14 Oct 2026

Breaking Bad: A Dataset for Geometric Fracture and Reassembly

arXiv 2210.11463 ↗First posted 20 Oct 2022cs.CV cs.GR cs.LGcited by 41

Not on the map. Why?

Abstract (arXiv)

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/.

Key facts. Cited by 41 papers in the map (data through 14 Oct 2026). Builds on 26 of its 88 references that are in the map. First posted on arXiv 20 Oct 2022.

Builds on

26 of 88 references.

References · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  5. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  7. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,270
  8. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  9. 2018Datasheets for Datasetscited by 1,386
  10. 2018PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understandingcited by 526
  11. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
  12. 2013DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognitioncited by 424
14 more
  1. 2020Rethinking Pre-training and Self-trainingcited by 352
  2. 2016Thingi10K: A Dataset of 10,000 3D-Printing Modelscited by 183
  3. 2019PQ-NET: A Generative Part Seq2Seq Network for 3D Shapescited by 119
  4. 2021JoinABLe: Learning Bottom-up Assembly of Parametric CAD Jointscited by 78
  5. 2020Generative 3D Part Assembly via Dynamic Graph Learningcited by 67
  6. 2020Learning 3D Part Assembly from a Single Imagecited by 52
  7. 2022Neural Shape Mating: Self-Supervised Object Assembly with Adversarial Shape Priorscited by 43
  8. 2019Learning Part Generation and Assembly for Structure-aware Shape Synthesiscited by 36
  9. 2021RGL-NET: A Recurrent Graph Learning framework for Progressive Part Assemblycited by 36
  10. 2020COALESCE: Component Assembly by Learning to Synthesize Connectionscited by 30
  11. 2022Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learningcited by 22
  12. 2021RoboAssembly: Learning Generalizable Furniture Assembly Policy in a Novel Multi-robot Contact-rich Simulation Environmentcited by 14
  13. 2022Bi-Manual Manipulation and Attachment via Sim-to-Real Reinforcement Learningcited by 14
  14. 2021Interactive Modelling of Volumetric Musculoskeletal Anatomycited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 12; 2025: 11; 2026: 10.

41 papers.

Sort:

By area:

  1. 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
  2. 2024DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassemblycited by 33
  3. 2023Jigsaw: Learning to Assemble Multiple Fractured Objectscited by 29
  4. 2023Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assemblycited by 28
  5. 2024Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solvingcited by 19
  6. 2023Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterpartscited by 18
  7. 2024PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verifycited by 15
  8. 2023Scalable Geometric Fracture Assembly via Co-creation Space among Assemblerscited by 14
  9. 2025Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Modelscited by 14
  10. 2025Rectified Point Flow: Generic Point Cloud Pose Estimationcited by 14
  11. 2025GARF: Learning Generalizable 3D Reassembly for Real-World Fracturescited by 13
  12. 2025Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulationcited by 13
29 more
  1. 2024SPAFormer: Sequential 3D Part Assembly with Transformerscited by 12
  2. 2024Sim2Real Manipulation on Unknown Objects with Tactile-based Reinforcement Learningcited by 11
  3. 20243D Geometric Shape Assembly via Efficient Point Cloud Matchingcited by 9
  4. 2024A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Partscited by 9
  5. 2024Jigsaw++: Imagining Complete Shape Priors for Object Reassemblycited by 6
  6. 2025BiAssemble: Learning Collaborative Affordance for Bimanual Geometric Assemblycited by 5
  7. 2025Manual2Skill++: Connector-Aware General Robotic Assembly from Instruction Manuals via Vision-Language Modelscited by 5
  8. 2024SE(3)-bi-equivariant Transformers for Point Cloud Assemblycited by 4
  9. 2026TORA: Topological Representation Alignment for 3D Shape Assemblycited by 4
  10. 2024Geometric Point Attention Transformer for 3D Shape Reassemblycited by 3
  11. 2025Combinative Matching for Geometric Shape Assemblycited by 3
  12. 2024GFPack++: Improving 2D Irregular Packing by Learning Gradient Field with Attentioncited by 2
  13. 2025Equivariant Flow Matching for Point Cloud Assemblycited by 2
  14. 2023Reassembling Broken Objects using Breaking Curvescited by 1
  15. 2023DeepFracture: A Generative Approach for Predicting Brittle Fractures with Neural Discrete Representation Learningcited by 1
  16. 2025E-M3RF: An Equivariant Multimodal 3D Re-assembly Frameworkcited by 1
  17. 2026CRAG: Can 3D Generative Models Help 3D Assembly?cited by 1
  18. 2026SARe: Structure-Aware Generative 3D Fragment Reassemblycited by 1
  19. 2023Pix2Repair: Implicit Shape Restoration from Imagescited by 0
  20. 20243D Shape Completion with Test-Time Trainingcited by 0
  21. 2025Neural Clustering for Prefractured Mesh Generation in Real-time Object Destructioncited by 0
  22. 2025Leveraging Pretrained Diffusion Models for Zero-Shot Part Assemblycited by 0
  23. 2026Transparent Fragments Contour Estimation via Visual-Tactile Fusion for Autonomous Reassemblycited by 0
  24. 2026Gmd: Gaussian mixture descriptor for pair matching of 3D fragmentscited by 0
  25. 2026Restore3D: Breathing Life into Broken Objects with Shape and Texture Restorationcited by 0
  26. 2026PVRA: A Pointwise Key-point Voting Framework for Robotic Assemblycited by 0
  27. 2026AssemblyWorld: Rethinking 3D Assembly with General-Purpose Agentscited by 0
  28. 2026LLM2R: From Large Language Models to 3D Reassemblerscited by 0
  29. 2026PhySGA: A Physics-Space Grounded Agentic Framework for Generalizable and Interactive 3D Compositioncited by 0