# GARF: Learning Generalizable 3D Reassembly for Real-World Fractures

arXiv: https://arxiv.org/abs/2504.05400 · HTML: https://mlsanity.com/paper/2504.05400/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 64 references that are in the map.
- First posted on arXiv 7 Apr 2025.

## Builds on (most cited first, 30 of 38)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [Flow Matching Guide and Code](https://mlsanity.com/paper/2412.06264/) (2024)
- [Multisample Flow Matching: Straightening Flows with Minibatch Couplings](https://mlsanity.com/paper/2304.14772/) (2023)
- [Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps](https://mlsanity.com/paper/2501.09732/) (2025)
- [SE(3) diffusion model with application to protein backbone generation](https://mlsanity.com/paper/2302.02277/) (2023)
- [PaliGemma 2: A Family of Versatile VLMs for Transfer](https://mlsanity.com/paper/2412.03555/) (2024)
- [BioCLIP: A Vision Foundation Model for the Tree of Life](https://mlsanity.com/paper/2311.18803/) (2023)
- [SE(3)-Stochastic Flow Matching for Protein Backbone Generation](https://mlsanity.com/paper/2310.02391/) (2023)
- [PQ-NET: A Generative Part Seq2Seq Network for 3D Shapes](https://mlsanity.com/paper/1911.10949/) (2019)
- [Golden Noise for Diffusion Models: A Learning Framework](https://mlsanity.com/paper/2411.09502/) (2024)
- [Not All Noises Are Created Equally:Diffusion Noise Selection and Optimization](https://mlsanity.com/paper/2407.14041/) (2024)
- [Generative 3D Part Assembly via Dynamic Graph Learning](https://mlsanity.com/paper/2006.07793/) (2020)
- [Proteina: Scaling Flow-based Protein Structure Generative Models](https://mlsanity.com/paper/2503.00710/) (2025)
- [Breaking Bad: A Dataset for Geometric Fracture and Reassembly](https://mlsanity.com/paper/2210.11463/) (2022)
- [Learning Part Generation and Assembly for Structure-aware Shape Synthesis](https://mlsanity.com/paper/1906.06693/) (2019)
- [Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Backbone Generation](https://mlsanity.com/paper/2405.20313/) (2024)
- [DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly](https://mlsanity.com/paper/2402.19302/) (2024)
- [All Seeds Are Not Equal: Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds](https://mlsanity.com/paper/2411.18810/) (2024)
- [Jigsaw: Learning to Assemble Multiple Fractured Objects](https://mlsanity.com/paper/2305.17975/) (2023)
- [Leveraging SE(3) Equivariance for Learning 3D Geometric Shape Assembly](https://mlsanity.com/paper/2309.06810/) (2023)

## Built on by (most cited first, 13 of 13)

- [Rectified Point Flow: Generic Point Cloud Pose Estimation](https://mlsanity.com/paper/2506.05282/) (2025)
- [Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching](https://mlsanity.com/paper/2512.01850/) (2025)
- [TORA: Topological Representation Alignment for 3D Shape Assembly](https://mlsanity.com/paper/2604.04050/) (2026)
- [Equivariant Flow Matching for Point Cloud Assembly](https://mlsanity.com/paper/2505.21539/) (2025)
- [Part2GS: Part-aware Modeling of Articulated Objects using 3D Gaussian Splatting](https://mlsanity.com/paper/2506.17212/) (2025)
- [E-M3RF: An Equivariant Multimodal 3D Re-assembly Framework](https://mlsanity.com/paper/2511.21422/) (2025)
- [Generative 6D Pose Estimation via Conditional Flow Matching](https://mlsanity.com/paper/2602.19719/) (2026)
- [SARe: Structure-Aware Generative 3D Fragment Reassembly](https://mlsanity.com/paper/2603.21611/) (2026)
- [Foundational feature fusion for conditional flow matching in 6D pose estimation](https://mlsanity.com/paper/2608.29183/) (2026)
- [PART: Learning 3D Part Assembly and Retrieval with Transformers](https://mlsanity.com/paper/2609.19872/) (2026)
- [A Unified Dual Method for Matching Problems](https://mlsanity.com/paper/2609.39339/) (2026)
- [AssemblyWorld: Rethinking 3D Assembly with General-Purpose Agents](https://mlsanity.com/paper/2609.40353/) (2026)
- [LLM2R: From Large Language Models to 3D Reassemblers](https://mlsanity.com/paper/2610.18604/) (2026)

## Abstract (arXiv)

3D reassembly is a challenging spatial intelligence task with broad applications across scientific domains. While large-scale synthetic datasets have fueled promising learning-based approaches, their generalizability to different domains is limited. Critically, it remains uncertain whether models trained on synthetic datasets can generalize to real-world fractures where breakage patterns are more complex. To bridge this gap, we propose GARF, a generalizable 3D reassembly framework for real-world fractures. GARF leverages fracture-aware pretraining to learn fracture features from individual fragments, with flow matching enabling precise 6-DoF alignments. At inference time, we introduce one-step preassembly, improving robustness to unseen objects and varying numbers of fractures. In collaboration with archaeologists, paleoanthropologists, and ornithologists, we curate Fractura, a diverse dataset for vision and learning communities, featuring real-world fracture types across ceramics, bones, eggshells, and lithics. Comprehensive experiments have shown our approach consistently outperforms state-of-the-art methods on both synthetic and real-world datasets, achieving 82.87% lower rotation error and 25.15% higher part accuracy. This sheds light on training on synthetic data to advance real-world 3D puzzle solving, demonstrating its strong generalization across unseen object shapes and diverse fracture types. GARF's code, data and demo are available at https://ai4ce.github.io/GARF/.