# GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation

arXiv: https://arxiv.org/abs/2508.14036 · HTML: https://mlsanity.com/paper/2508.14036/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 36 references that are in the map.
- First posted on arXiv 19 Aug 2025.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding](https://mlsanity.com/paper/1812.02713/) (2018)
- [TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models](https://mlsanity.com/paper/2502.06608/) (2025)
- [PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning](https://mlsanity.com/paper/2211.11682/) (2022)
- [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)
- [Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels](https://mlsanity.com/paper/2312.17232/) (2023)
- [SATR: Zero-Shot Semantic Segmentation of 3D Shapes](https://mlsanity.com/paper/2304.04909/) (2023)
- [Segment Anything in 3D with Radiance Fields](https://mlsanity.com/paper/2304.12308/) (2023)
- [Point-SAM: Promptable 3D Segmentation Model for Point Clouds](https://mlsanity.com/paper/2406.17741/) (2024)
- [Better Call SAL: Towards Learning to Segment Anything in Lidar](https://mlsanity.com/paper/2403.13129/) (2024)
- [SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2311.17707/) (2023)
- [PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimation](https://mlsanity.com/paper/2312.03015/) (2023)
- [Segment Any Mesh](https://mlsanity.com/paper/2408.13679/) (2024)
- [PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision](https://mlsanity.com/paper/2303.09554/) (2023)
- [PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation](https://mlsanity.com/paper/2312.04016/) (2023)
- [MeshSegmenter: Zero-Shot Mesh Semantic Segmentation via Texture Synthesis](https://mlsanity.com/paper/2407.13675/) (2024)
- [SANeRF-HQ: Segment Anything for NeRF in High Quality](https://mlsanity.com/paper/2312.01531/) (2023)
- [ZeroPS: High-quality Cross-modal Knowledge Transfer for Zero-Shot 3D Part Segmentation](https://mlsanity.com/paper/2311.14262/) (2023)
- [3D Part Segmentation via Geometric Aggregation of 2D Visual Features](https://mlsanity.com/paper/2412.04247/) (2024)
- [CoSeg: Cognitively Inspired Unsupervised Generic Event Segmentation](https://mlsanity.com/paper/2109.15170/) (2021)
- [Open-Vocabulary Part-Based Grasping](https://mlsanity.com/paper/2406.05951/) (2024)
- [Neural ShDF: Reviving an Efficient and Consistent Mesh Segmentation Method](https://mlsanity.com/paper/2306.11737/) (2023)

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

- [HY3D-Bench: Generation of 3D Assets](https://mlsanity.com/paper/2602.03907/) (2026)
- [SegviGen: Repurposing 3D Generative Model for Part Segmentation](https://mlsanity.com/paper/2603.16869/) (2026)
- [UniPart: Part-Level 3D Generation with Unified 3D Geom-Seg Latents](https://mlsanity.com/paper/2512.09435/) (2025)
- [Video Understanding: From Geometry and Semantics to Unified Models](https://mlsanity.com/paper/2603.17840/) (2026)
- [Universal 3D Shape Matching via Coarse-to-Fine Language Guidance](https://mlsanity.com/paper/2602.19112/) (2026)
- [CoSMo3D: Open-World Promptable 3D Semantic Part Segmentation through LLM-Guided Canonical Spatial Modeling](https://mlsanity.com/paper/2603.01205/) (2026)
- [Part-Level 3D Gaussian Vehicle Generation with Joint and Hinge Axis Estimation](https://mlsanity.com/paper/2604.05070/) (2026)
- [FoundYou: A Unified Model for Personalized Segmentation and Retrieval](https://mlsanity.com/paper/2608.29917/) (2026)
- [Seg3DParts: Segmentation-Grounded Controllable Part-Level 3D Generation](https://mlsanity.com/paper/2609.36918/) (2026)
- [EviRover: Reinforcing Agentic Perception Beyond a Glance](https://mlsanity.com/paper/2609.40230/) (2026)
- [Organize Primitives into Semantic Parts: Reinforcement Reasoning for 3D Segmentation](https://mlsanity.com/paper/2610.04602/) (2026)
- [DistScene: Object-to-Scene Distillation for 3D Scene Generation](https://mlsanity.com/paper/2610.06960/) (2026)
- [ScenePlacer: Reformulating Scene-Level Object Pose Estimation as Visibility Field Learning](https://mlsanity.com/paper/2610.15734/) (2026)

## Abstract (arXiv)

We introduce GeoSAM2, a prompt-controllable framework for 3D part segmentation that casts the task as multi-view 2D mask prediction. Given a textureless object, we render normal and point maps from predefined viewpoints and accept simple 2D prompts - clicks or boxes - to guide part selection. These prompts are processed by a shared SAM2 backbone augmented with LoRA and residual geometry fusion, enabling view-specific reasoning while preserving pretrained priors. The predicted masks are back-projected to the object and aggregated across views. Our method enables fine-grained, part-specific control without requiring text prompts, per-shape optimization, or full 3D labels. In contrast to global clustering or scale-based methods, prompts are explicit, spatially grounded, and interpretable. We achieve state-of-the-art class-agnostic performance on PartObjaverse-Tiny and PartNetE, outperforming both slow optimization-based pipelines and fast but coarse feedforward approaches. Our results highlight a new paradigm: aligning the paradigm of 3D segmentation with SAM2, leveraging interactive 2D inputs to unlock controllability and precision in object-level part understanding.