# Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting

arXiv: https://arxiv.org/abs/2503.22204 · HTML: https://mlsanity.com/paper/2503.22204/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 45 references that are in the map.
- First posted on arXiv 28 Mar 2025.

## Builds on (most cited first, 30 of 34)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [HexPlane: A Fast Representation for Dynamic Scenes](https://mlsanity.com/paper/2301.09632/) (2023)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting](https://mlsanity.com/paper/2310.10642/) (2023)
- [LangSplat: 3D Language Gaussian Splatting](https://mlsanity.com/paper/2312.16084/) (2023)
- [Gaussian Grouping: Segment and Edit Anything in 3D Scenes](https://mlsanity.com/paper/2312.00732/) (2023)
- [Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields](https://mlsanity.com/paper/2312.03203/) (2023)
- [Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis](https://mlsanity.com/paper/2312.16812/) (2023)
- [OpenMask3D: Open-Vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2306.13631/) (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)
- [Weakly Supervised 3D Open-vocabulary Segmentation](https://mlsanity.com/paper/2305.14093/) (2023)
- [Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation](https://mlsanity.com/paper/2308.07931/) (2023)
- [SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory](https://mlsanity.com/paper/2411.11922/) (2024)
- [Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping](https://mlsanity.com/paper/2309.07970/) (2023)
- [FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding](https://mlsanity.com/paper/2401.01970/) (2024)
- [GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping](https://mlsanity.com/paper/2403.09637/) (2024)
- [Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels](https://mlsanity.com/paper/2312.17232/) (2023)
- [Feature Splatting: Language-Driven Physics-Based Scene Synthesis and Editing](https://mlsanity.com/paper/2404.01223/) (2024)
- [GraspSplats: Efficient Manipulation with 3D Feature Splatting](https://mlsanity.com/paper/2409.02084/) (2024)
- [4D LangSplat: 4D Language Gaussian Splatting via Multimodal Large Language Models](https://mlsanity.com/paper/2503.10437/) (2025)
- [GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting](https://mlsanity.com/paper/2411.07555/) (2024)

## Built on by (most cited first, 8 of 8)

- [4D Synchronized Fields: Motion-Language Gaussian Splatting for Temporal Scene Understanding](https://mlsanity.com/paper/2603.14301/) (2026)
- [TrackRef3D: Multi-View Consistent Track-then-Label for Open-World Referring Segmentation in 3D Gaussian Splatting](https://mlsanity.com/paper/2605.26576/) (2026)
- [G2P: Gaussian-to-Point Attribute Alignment for Boundary-Aware 3D Segmentation](https://mlsanity.com/paper/2601.03510/) (2026)
- [AdvSplat: Adversarial Attacks on Feed-Forward Gaussian Splatting Models](https://mlsanity.com/paper/2603.23686/) (2026)
- [Consistent Scene Understanding in 3D Gaussian Splatting via Multi-Cue Mask Refinement](https://mlsanity.com/paper/2607.01708/) (2026)
- [Beyond Similarity Matching: Structured Reasoning for Open-Vocabulary Referring Segmentation in 3DGS](https://mlsanity.com/paper/2608.16103/) (2026)
- [Hybrid Gaussians for Robust Open-Vocabulary 3D Segmentation with Multi-View Object Association and Boundary Refinement](https://mlsanity.com/paper/2609.27462/) (2026)
- [DIGS: Distribution-Informed Gaussian Splatting for Training-Free Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2610.16177/) (2026)

## Abstract (arXiv)

Open-vocabulary querying in 3D space is crucial for enabling more intelligent perception in applications such as robotics, autonomous systems, and augmented reality. However, most existing methods rely on 2D pixel-level parsing, leading to multi-view inconsistencies and poor 3D object retrieval. Moreover, they are limited to static scenes and struggle with dynamic scenes due to the complexities of motion modeling. In this paper, we propose Segment then Splat, a 3D-aware open vocabulary segmentation approach for both static and dynamic scenes based on Gaussian Splatting. Segment then Splat reverses the long established approach of "segmentation after reconstruction" by dividing Gaussians into distinct object sets before reconstruction. Once reconstruction is complete, the scene is naturally segmented into individual objects, achieving true 3D segmentation. This design eliminates both geometric and semantic ambiguities, as well as Gaussian-object misalignment issues in dynamic scenes. It also accelerates the optimization process, as it eliminates the need for learning a separate language field. After optimization, a CLIP embedding is assigned to each object to enable open-vocabulary querying. Extensive experiments one various datasets demonstrate the effectiveness of our proposed method in both static and dynamic scenarios.