# ExtrinSplat: Decoupling Geometry and Semantics for Open-Vocabulary Understanding in 3D Gaussian Splatting

arXiv: https://arxiv.org/abs/2509.22225 · HTML: https://mlsanity.com/paper/2509.22225/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 36 references that are in the map.
- First posted on arXiv 26 Sep 2025.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [LangSplat: 3D Language Gaussian Splatting](https://mlsanity.com/paper/2312.16084/) (2023)
- [Extracting Triangular 3D Models, Materials, and Lighting From Images](https://mlsanity.com/paper/2111.12503/) (2021)
- [Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields](https://mlsanity.com/paper/2312.03203/) (2023)
- [Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding](https://mlsanity.com/paper/2311.18482/) (2023)
- [OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding](https://mlsanity.com/paper/2406.02058/) (2024)
- [RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics](https://mlsanity.com/paper/2411.16537/) (2024)
- [A Distractor-Aware Memory for Visual Object Tracking with SAM2](https://mlsanity.com/paper/2411.17576/) (2024)
- [FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally](https://mlsanity.com/paper/2409.08270/) (2024)
- [Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving](https://mlsanity.com/paper/2405.05258/) (2024)
- [GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane](https://mlsanity.com/paper/2405.17596/) (2024)
- [Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration](https://mlsanity.com/paper/2502.16652/) (2025)
- [Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Driving](https://mlsanity.com/paper/2303.17297/) (2023)
- [LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes](https://mlsanity.com/paper/2410.14462/) (2024)
- [InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception](https://mlsanity.com/paper/2411.19235/) (2024)
- [SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians](https://mlsanity.com/paper/2412.10231/) (2024)
- [SUGAR: Pre-training 3D Visual Representations for Robotics](https://mlsanity.com/paper/2404.01491/) (2024)
- [COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian Splitting](https://mlsanity.com/paper/2503.19443/) (2025)
- [Occam's LGS: An Efficient Approach for Language Gaussian Splatting](https://mlsanity.com/paper/2412.01807/) (2024)
- [Tackling View-Dependent Semantics in 3D Language Gaussian Splatting](https://mlsanity.com/paper/2505.24746/) (2025)
- [GradiSeg: Gradient-Guided Gaussian Segmentation with Enhanced 3D Boundary Precision](https://mlsanity.com/paper/2412.00392/) (2024)

## Built on by (most cited first, 6 of 6)

- [ZeroSplat: Generalized Referring Segmentation in 3D Gaussian Splatting](https://mlsanity.com/paper/2607.18801/) (2026)
- [LMM-Track4D: Eliciting 4D Dynamic Reasoning in LMMs via Trajectory-Grounded Dialogue](https://mlsanity.com/paper/2605.19390/) (2026)
- [Relation-Centric Open-Vocabulary 3D Gaussian Segmentation](https://mlsanity.com/paper/2607.01140/) (2026)
- [EndoMD-SLAM: Endoscopic Gaussian Splatting SLAM under Optical Degradation with Memory and Static-Transient Decomposition](https://mlsanity.com/paper/2608.08949/) (2026)
- [Dyn-3D: Unveiling and Resolving Ego-Motion Ambiguity in Vision-Language Models](https://mlsanity.com/paper/2609.01059/) (2026)
- [DIGS: Distribution-Informed Gaussian Splatting for Training-Free Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2610.16177/) (2026)

## Abstract (arXiv)

Lifting 2D open-vocabulary understanding into 3D Gaussian Splatting (3DGS) scenes is a critical challenge. Mainstream methods, built on an embedding paradigm, suffer from three key flaws: (i) geometry-semantic inconsistency, where points, rather than objects, serve as the semantic basis, limiting semantic fidelity; (ii) semantic bloat from injecting gigabytes of feature data into the geometry; and (iii) semantic rigidity, as one feature per Gaussian struggles to capture rich polysemy. To overcome these limitations, we introduce ExtrinSplat, a framework built on the extrinsic paradigm that decouples geometry from semantics. Instead of embedding features, ExtrinSplat clusters Gaussians into multi-granularity, overlapping 3D object groups. A Vision-Language Model (VLM) then interprets these groups to generate lightweight textual hypotheses, creating an extrinsic index layer that natively supports complex polysemy. By replacing costly feature embedding with lightweight indices, ExtrinSplat reduces scene adaptation time from hours to minutes and lowers storage overhead by several orders of magnitude. On benchmark tasks for open-vocabulary 3D object selection and semantic segmentation, ExtrinSplat outperforms established embedding-based frameworks, validating the efficacy and efficiency of the proposed extrinsic paradigm.