# Learning Fine-Grained Segmentation of 3D Shapes without Part Labels

arXiv: https://arxiv.org/abs/2103.13030 · HTML: https://mlsanity.com/paper/2103.13030/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 24 Mar 2021.

## Builds on (most cited first, 16 of 16)

- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [Graph Neural Networks: A Review of Methods and Applications](https://mlsanity.com/paper/1812.08434/) (2018)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs](https://mlsanity.com/paper/1711.09869/) (2017)
- [SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation](https://mlsanity.com/paper/1711.08588/) (2017)
- [GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud](https://mlsanity.com/paper/1812.03320/) (2018)
- [PartNet: A Recursive Part Decomposition Network for Fine-grained and Hierarchical Shape Segmentation](https://mlsanity.com/paper/1903.00709/) (2019)
- [Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories](https://mlsanity.com/paper/2002.06478/) (2020)
- [SCORES: Shape Composition with Recursive Substructure Priors](https://mlsanity.com/paper/1809.05398/) (2018)
- [Faces as Lighting Probes via Unsupervised Deep Highlight Extraction](https://mlsanity.com/paper/1803.06340/) (2018)
- [Learning to Group and Label Fine-Grained Shape Components](https://mlsanity.com/paper/1809.05050/) (2018)
- [Data-Driven Shape Analysis and Processing](https://mlsanity.com/paper/1502.06686/) (2015)
- [Triangle Lasso for Simultaneous Clustering and Optimization in Graph Datasets](https://mlsanity.com/paper/1808.06556/) (2018)

## Built on by (most cited first, 14 of 14)

- [PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models](https://mlsanity.com/paper/2212.01558/) (2022)
- [SAMPart3D: Segment Any Part in 3D Objects](https://mlsanity.com/paper/2411.07184/) (2024)
- [PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond](https://mlsanity.com/paper/2504.11451/) (2025)
- [PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimation](https://mlsanity.com/paper/2312.03015/) (2023)
- [PartGlot: Learning Shape Part Segmentation from Language Reference Games](https://mlsanity.com/paper/2112.06390/) (2021)
- [ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation](https://mlsanity.com/paper/2311.14262/) (2023)
- [3D Compositional Zero-shot Learning with DeCompositional Consensus](https://mlsanity.com/paper/2111.14673/) (2021)
- [Iterative Superquadric Recomposition of 3D Objects from Multiple Views](https://mlsanity.com/paper/2309.02102/) (2023)
- [DisARM: Displacement Aware Relation Module for 3D Detection](https://mlsanity.com/paper/2203.01152/) (2022)
- [HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling](https://mlsanity.com/paper/2301.10460/) (2023)
- [SHRED: 3D Shape Region Decomposition with Learned Local Operations](https://mlsanity.com/paper/2206.03480/) (2022)
- [Isomorphic mesh generation from point clouds with multilayer perceptrons](https://mlsanity.com/paper/2210.14157/) (2022)
- [Analogy-Forming Transformers for Few-Shot 3D Parsing](https://mlsanity.com/paper/2304.14382/) (2023)
- [PinPoint3D: Fine-Grained 3D Part Segmentation from a Few Clicks](https://mlsanity.com/paper/2509.25970/) (2025)

## Abstract (arXiv)

Learning-based 3D shape segmentation is usually formulated as a semantic labeling problem, assuming that all parts of training shapes are annotated with a given set of tags. This assumption, however, is impractical for learning fine-grained segmentation. Although most off-the-shelf CAD models are, by construction, composed of fine-grained parts, they usually miss semantic tags and labeling those fine-grained parts is extremely tedious. We approach the problem with deep clustering, where the key idea is to learn part priors from a shape dataset with fine-grained segmentation but no part labels. Given point sampled 3D shapes, we model the clustering priors of points with a similarity matrix and achieve part segmentation through minimizing a novel low rank loss. To handle highly densely sampled point sets, we adopt a divide-and-conquer strategy. We partition the large point set into a number of blocks. Each block is segmented using a deep-clustering-based part prior network trained in a category-agnostic manner. We then train a graph convolution network to merge the segments of all blocks to form the final segmentation result. Our method is evaluated with a challenging benchmark of fine-grained segmentation, showing state-of-the-art performance.