# Semantic 3D scene understanding and robotics

Area: [3D reconstruction and neural rendering](https://mlsanity.com/recon3d/index.md). HTML: https://mlsanity.com/recon3d/semantic-3d-scene-understanding-and-robotics/

## Key facts

- Semantic 3D scene understanding and robotics: 527 papers on arXiv since 2021 (data through 19 Oct 2026).
- 161 of its 527 mapped papers (31%) cite “LangSplat: 3D Language Gaussian Splatting” (2023, arXiv 2312.16084).
- 140 of its 527 mapped papers (27%) cite “Gaussian Grouping: Segment and Edit Anything in 3D Scenes” (2023, arXiv 2312.00732).
- 9 new papers 1 Oct–19 Oct.

## Most cited here

- [LangSplat: 3D Language Gaussian Splatting](https://mlsanity.com/paper/2312.16084/) (2023), cited by 161 papers here
- [Gaussian Grouping: Segment and Edit Anything in 3D Scenes](https://mlsanity.com/paper/2312.00732/) (2023), cited by 140 papers here
- [OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding](https://mlsanity.com/paper/2406.02058/) (2024), cited by 74 papers here
- [Weakly Supervised 3D Open-vocabulary Segmentation](https://mlsanity.com/paper/2305.14093/) (2023), cited by 68 papers here
- [GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting](https://mlsanity.com/paper/2311.14521/) (2023), cited by 66 papers here
- [Segment Any 3D Gaussians](https://mlsanity.com/paper/2312.00860/) (2023), cited by 57 papers here
- [FMGS: Foundation Model Embedded 3D Gaussian Splatting for Holistic 3D Scene Understanding](https://mlsanity.com/paper/2401.01970/) (2024), cited by 44 papers here
- [GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane](https://mlsanity.com/paper/2405.17596/) (2024), cited by 33 papers here
- [Splat-Nav: Safe Real-Time Robot Navigation in Gaussian Splatting Maps](https://mlsanity.com/paper/2403.02751/) (2024), cited by 32 papers here
- [GaussianGrasper: 3D Language Gaussian Splatting for Open-vocabulary Robotic Grasping](https://mlsanity.com/paper/2403.09637/) (2024), cited by 31 papers here

## New (1 Oct–19 Oct)

- [YUBI-Real2Sim: 3DGS Scene Verification for Reliable Policy Evaluation](https://mlsanity.com/paper/2610.17521/) (2026-10-13)
- [G2WAM: World Action Models for Efficient and Geometry Grounded Image-Goal Navigation](https://mlsanity.com/paper/2610.16558/) (2026-10-12)
- [DIGS: Distribution-Informed Gaussian Splatting for Training-Free Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2610.16177/) (2026-10-12)
- [FlowVLA: Enabling World Dynamics Understanding through Pluggable 3D Flow Learning](https://mlsanity.com/paper/2610.16160/) (2026-10-12)
- [NovaSplat: Model-Free 6D Object Pose Estimation via 3D Gaussian Splatting Onboarding and Refinement](https://mlsanity.com/paper/2610.13309/) (2026-10-09)
- [Post-Training Semantic Lifting for 3D Gaussian Splatting: Separating Detector, Lifting and Representation Error](https://mlsanity.com/paper/2610.08756/) (2026-10-06)
- [LoCoSplat: Real-Time Feed-Forward 3D Gaussian Splatting with Minimal 3D Reasoning](https://mlsanity.com/paper/2610.04351/) (2026-10-03)
- [3DROID: A Renderable 3D Gaussian Dataset with Measured Per-Scene Reliability](https://mlsanity.com/paper/2610.01744/) (2026-10-01)
- [RelationVGGT: Visual Geometry Transformers for 3D Spatial Relation Segmentation](https://mlsanity.com/paper/2610.00970/) (2026-10-01)