# SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation

arXiv: https://arxiv.org/abs/2311.17707 · HTML: https://mlsanity.com/paper/2311.17707/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 77 of its 96 references that are in the map.
- First posted on arXiv 29 Nov 2023.

## Builds on (most cited first, 30 of 77)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [KPConv: Flexible and Deformable Convolution for Point Clouds](https://mlsanity.com/paper/1904.08889/) (2019)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [PointCNN: Convolution On X-Transformed Points](https://mlsanity.com/paper/1801.07791/) (2018)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [PointConv: Deep Convolutional Networks on 3D Point Clouds](https://mlsanity.com/paper/1811.07246/) (2018)
- [Deep Hough Voting for 3D Object Detection in Point Clouds](https://mlsanity.com/paper/1904.09664/) (2019)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)

## Built on by (most cited first, 30 of 44)

- [Open3DIS: Open-Vocabulary 3D Instance Segmentation with 2D Mask Guidance](https://mlsanity.com/paper/2312.10671/) (2023)
- [PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond](https://mlsanity.com/paper/2504.11451/) (2025)
- [DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning](https://mlsanity.com/paper/2503.15265/) (2025)
- [Point-SAM: Promptable 3D Segmentation Model for Point Clouds](https://mlsanity.com/paper/2406.17741/) (2024)
- [P3-SAM: Native 3D Part Segmentation](https://mlsanity.com/paper/2509.06784/) (2025)
- [EmbodiedSAM: Online Segment Any 3D Thing in Real Time](https://mlsanity.com/paper/2408.11811/) (2024)
- [Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D](https://mlsanity.com/paper/2504.14151/) (2025)
- [SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners](https://mlsanity.com/paper/2408.16768/) (2024)
- [Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking](https://mlsanity.com/paper/2411.16183/) (2024)
- [Unifying 2D and 3D Vision-Language Understanding](https://mlsanity.com/paper/2503.10745/) (2025)
- [AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splatting](https://mlsanity.com/paper/2502.04981/) (2025)
- [GeoSAM2: Unleashing the Power of SAM2 for 3D Part Segmentation](https://mlsanity.com/paper/2508.14036/) (2025)
- [3x2: 3D Object Part Segmentation by 2D Semantic Correspondences](https://mlsanity.com/paper/2407.09648/) (2024)
- [Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2504.19500/) (2025)
- [SegviGen: Repurposing 3D Generative Model for Part Segmentation](https://mlsanity.com/paper/2603.16869/) (2026)
- [PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Models](https://mlsanity.com/paper/2403.06403/) (2024)
- [Open-Vocabulary SAM3D: Towards Training-free Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2405.15580/) (2024)
- [From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs](https://mlsanity.com/paper/2502.20389/) (2025)
- [RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation](https://mlsanity.com/paper/2410.11722/) (2024)
- [OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction](https://mlsanity.com/paper/2509.23541/) (2025)
- [Online Segment Any 3D Thing as Instance Tracking](https://mlsanity.com/paper/2512.07599/) (2025)
- [3AM: 3egment Anything with Geometric Consistency in Videos](https://mlsanity.com/paper/2601.08831/) (2026)
- [SA3DIP: Segment Any 3D Instance with Potential 3D Priors](https://mlsanity.com/paper/2411.03819/) (2024)
- [econSG: Efficient and Multi-view Consistent Open-Vocabulary 3D Semantic Gaussians](https://mlsanity.com/paper/2504.06003/) (2025)
- [ShelfGaussian: Shelf-Supervised Open-Vocabulary Gaussian-based 3D Scene Understanding](https://mlsanity.com/paper/2512.03370/) (2025)
- [Pro2SAM: Mask Prompt to SAM with Grid Points for Weakly Supervised Object Localization](https://mlsanity.com/paper/2505.04905/) (2025)
- [FloorSAM: SAM-Guided Floorplan Reconstruction with Semantic-Geometric Fusion](https://mlsanity.com/paper/2509.15750/) (2025)
- [EI-Part: Explode for Completion and Implode for Refinement](https://mlsanity.com/paper/2603.14021/) (2026)
- [MV3DIS: Multi-View Mask Matching via 3D Guides for Zero-Shot 3D Instance Segmentation](https://mlsanity.com/paper/2604.08916/) (2026)
- [ESAM++: Efficient Online 3D Perception on the Edge](https://mlsanity.com/paper/2605.29505/) (2026)

## Abstract (arXiv)

We introduce SAMPro3D for zero-shot instance segmentation of 3D scenes. Given the 3D point cloud and multiple posed RGB-D frames of 3D scenes, our approach segments 3D instances by applying the pretrained Segment Anything Model (SAM) to 2D frames. Our key idea involves locating SAM prompts in 3D to align their projected pixel prompts across frames, ensuring the view consistency of SAM-predicted masks. Moreover, we suggest selecting prompts from the initial set guided by the information of SAM-predicted masks across all views, which enhances the overall performance. We further propose to consolidate different prompts if they are segmenting different surface parts of the same 3D instance, bringing a more comprehensive segmentation. Notably, our method does not require any additional training. Extensive experiments on diverse benchmarks show that our method achieves comparable or better performance compared to previous zero-shot or fully supervised approaches, and in many cases surpasses human annotations. Furthermore, since our fine-grained predictions often lack annotations in available datasets, we present ScanNet200-Fine50 test data which provides fine-grained annotations on 50 scenes from ScanNet200 dataset. The project page can be accessed at https://mutianxu.github.io/sampro3d/.