# EmbodiedSAM: Online Segment Any 3D Thing in Real Time

arXiv: https://arxiv.org/abs/2408.11811 · HTML: https://mlsanity.com/paper/2408.11811/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 40 references that are in the map.
- First posted on arXiv 21 Aug 2024.

## Builds on (most cited first, 30 of 33)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [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)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [3D Semantic Segmentation with Submanifold Sparse Convolutional Networks](https://mlsanity.com/paper/1711.10275/) (2017)
- [Segment Everything Everywhere All at Once](https://mlsanity.com/paper/2304.06718/) (2023)
- [Object Goal Navigation using Goal-Oriented Semantic Exploration](https://mlsanity.com/paper/2007.00643/) (2020)
- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [OpenMask3D: Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2306.13631/) (2023)
- [Language-Grounded Indoor 3D Semantic Segmentation in the Wild](https://mlsanity.com/paper/2204.07761/) (2022)
- [6-DOF GraspNet: Variational Grasp Generation for Object Manipulation](https://mlsanity.com/paper/1905.10520/) (2019)
- [RIO: 3D Object Instance Re-Localization in Changing Indoor Environments](https://mlsanity.com/paper/1908.06109/) (2019)
- [Semantic-SAM: Segment and Recognize Anything at Any Granularity](https://mlsanity.com/paper/2307.04767/) (2023)
- [SAM3D: Segment Anything in 3D Scenes](https://mlsanity.com/paper/2306.03908/) (2023)
- [SemanticFusion: Dense 3D Semantic Mapping with Convolutional Neural Networks](https://mlsanity.com/paper/1609.05130/) (2016)
- [Superpoint Transformer for 3D Scene Instance Segmentation](https://mlsanity.com/paper/2211.15766/) (2022)
- [Accelerated Hierarchical Density Clustering](https://mlsanity.com/paper/1705.07321/) (2017)
- [GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields](https://mlsanity.com/paper/2308.16891/) (2023)
- [PanopticFusion: Online Volumetric Semantic Mapping at the Level of Stuff and Things](https://mlsanity.com/paper/1903.01177/) (2019)
- [OneFormer3D: One Transformer for Unified Point Cloud Segmentation](https://mlsanity.com/paper/2311.14405/) (2023)
- [SAI3D: Segment Any Instance in 3D Scenes](https://mlsanity.com/paper/2312.11557/) (2023)
- [OVIR-3D: Open-Vocabulary 3D Instance Retrieval Without Training on 3D Data](https://mlsanity.com/paper/2311.02873/) (2023)
- [3D-Aware Object Goal Navigation via Simultaneous Exploration and Identification](https://mlsanity.com/paper/2212.00338/) (2022)
- [SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2311.17707/) (2023)
- [Fusion-Aware Point Convolution for Online Semantic 3D Scene Segmentation](https://mlsanity.com/paper/2003.06233/) (2020)
- [TR3D: Towards Real-Time Indoor 3D Object Detection](https://mlsanity.com/paper/2302.02858/) (2023)

## Built on by (most cited first, 30 of 40)

- [SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation](https://mlsanity.com/paper/2410.08189/) (2024)
- [PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond](https://mlsanity.com/paper/2504.11451/) (2025)
- [SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree](https://mlsanity.com/paper/2410.16268/) (2024)
- [Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation](https://mlsanity.com/paper/2507.04047/) (2025)
- [UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility](https://mlsanity.com/paper/2501.02341/) (2025)
- [Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation](https://mlsanity.com/paper/2505.11383/) (2025)
- [On Efficient Variants of Segment Anything Model: A Survey](https://mlsanity.com/paper/2410.04960/) (2024)
- [ROS-SAM: High-Quality Interactive Segmentation for Remote Sensing Moving Object](https://mlsanity.com/paper/2503.12006/) (2025)
- [OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging](https://mlsanity.com/paper/2503.01309/) (2025)
- [Relation3D: Enhancing Relation Modeling for Point Cloud Instance Segmentation](https://mlsanity.com/paper/2506.17891/) (2025)
- [PartUV: Part-Based UV Unwrapping of 3D Meshes](https://mlsanity.com/paper/2511.16659/) (2025)
- [Occupancy World Model for Robots](https://mlsanity.com/paper/2505.05512/) (2025)
- [CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting](https://mlsanity.com/paper/2412.19142/) (2024)
- [Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field](https://mlsanity.com/paper/2502.16303/) (2025)
- [MoSAM: Motion-Guided Segment Anything Model with Spatial-Temporal Memory Selection](https://mlsanity.com/paper/2505.00739/) (2025)
- [DCHM: Depth-Consistent Human Modeling for Multiview Detection](https://mlsanity.com/paper/2507.14505/) (2025)
- [Semantic Consistent Language Gaussian Splatting for Point-Level Open-vocabulary Querying](https://mlsanity.com/paper/2503.21767/) (2025)
- [EA3D: Online Open-World 3D Object Extraction from Streaming Videos](https://mlsanity.com/paper/2510.25146/) (2025)
- [Online Segment Any 3D Thing as Instance Tracking](https://mlsanity.com/paper/2512.07599/) (2025)
- [MoonSeg3R: Monocular Online Zero-Shot Segment Anything in 3D with Reconstructive Foundation Priors](https://mlsanity.com/paper/2512.15577/) (2025)
- [3AM: 3egment Anything with Geometric Consistency in Videos](https://mlsanity.com/paper/2601.08831/) (2026)
- [OpenFusion++: An Open-vocabulary Real-time Scene Understanding System](https://mlsanity.com/paper/2504.19266/) (2025)
- [BoxFusion: Reconstruction-Free Open-Vocabulary 3D Object Detection via Real-Time Multi-View Box Fusion](https://mlsanity.com/paper/2506.15610/) (2025)
- [Fake It To Make It: Virtual Multiviews to Enhance Monocular Indoor Semantic Scene Completion](https://mlsanity.com/paper/2503.05086/) (2025)
- [OnlinePG: Online Open-Vocabulary Panoptic Mapping with 3D Gaussian Splatting](https://mlsanity.com/paper/2603.18510/) (2026)
- [SpaCeFormer: Fast Proposal-Free Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2604.20395/) (2026)
- [Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling](https://mlsanity.com/paper/2608.30821/) (2026)
- [Towards Fine-grained Interactive Segmentation in Images and Videos](https://mlsanity.com/paper/2502.09660/) (2025)
- [EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2603.04254/) (2026)
- [EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision](https://mlsanity.com/paper/2605.13152/) (2026)

## Abstract (arXiv)

Embodied tasks require the agent to fully understand 3D scenes simultaneously with its exploration, so an online, real-time, fine-grained and highly-generalized 3D perception model is desperately needed. Since high-quality 3D data is limited, directly training such a model in 3D is almost infeasible. Meanwhile, vision foundation models (VFM) has revolutionized the field of 2D computer vision with superior performance, which makes the use of VFM to assist embodied 3D perception a promising direction. However, most existing VFM-assisted 3D perception methods are either offline or too slow that cannot be applied in practical embodied tasks. In this paper, we aim to leverage Segment Anything Model (SAM) for real-time 3D instance segmentation in an online setting. This is a challenging problem since future frames are not available in the input streaming RGB-D video, and an instance may be observed in several frames so object matching between frames is required. To address these challenges, we first propose a geometric-aware query lifting module to represent the 2D masks generated by SAM by 3D-aware queries, which is then iteratively refined by a dual-level query decoder. In this way, the 2D masks are transferred to fine-grained shapes on 3D point clouds. Benefit from the query representation for 3D masks, we can compute the similarity matrix between the 3D masks from different views by efficient matrix operation, which enables real-time inference. Experiments on ScanNet, ScanNet200, SceneNN and 3RScan show our method achieves leading performance even compared with offline methods. Our method also demonstrates great generalization ability in several zero-shot dataset transferring experiments and show great potential in open-vocabulary and data-efficient setting. Code and demo are available at https://xuxw98.github.io/ESAM/, with only one RTX 3090 GPU required for training and evaluation.