Research map / 3D vision / Gaussian splatting
Gaussian Grouping: Segment and Edit Anything in 3D Scenes
Mingqiao Ye, Martin Danelljan, Fisher Yu, Lei Ke
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add 3D regularization loss with K=5 nearest neighbors (ablation) | Gaussian Grouping · Mip-NeRF 360 Kitchen object removal | RAcc: 41.2% -> 76.6% | Improved |
| increase K from 5 to 10 (ablation) | 3D regularization loss · Mip-NeRF 360 Kitchen object removal | RAcc: 76.6% -> 77.8% | No clear effect |
| add 3D Identity/Regularization loss to 2D identity loss (ablation) | Gaussian Grouping · Bear inpainting | qualitative | Improved |
| use video-tracker mask association instead of cost-based linear assignment (ablation) | Gaussian Grouping · 2K training iterations | training time: 1 hour -> 1 minute | Improved |
| joint training of Identity Encoding with Gaussian Splatting | Gaussian Splatting · Mip-NeRF 360 (7 scenes) | PSNR: 28.69 -> 28.43 | No clear effect |
| double Identity Encoding dimension from 16 to 32 (ablation) | Gaussian Grouping · Mip-NeRF 360 | reconstruction quality and training time: training 1.3 times slower | No clear effect |
| use Gaussian Grouping instead of SA3D for segmentation | SA3D · LERF-Mask ramen | mIoU: 7.4 -> 77.0 | Improved |
| use Gaussian Grouping instead of Panoptic Lifting | Panoptic Lifting · Replica panoptic | mIoU (%): 66.22 -> 71.15 | Improved |
Later papers that compared with this method
19 later accepted papers report Gaussian Grouping as a baseline in their results tables; 17 of them report a better number on most of the results they share with it.
- Evolving Semantic Propagation for Aerial Semantic 3D Gaussian Splatting (AAAI 2026 · better on 9 of 9 shared results)
- Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field (IJCV 2026 · better on 9 of 9 shared results)
- GPGS: Consistent 3D Object Removal via Geometry-Aware 3D Inpainting and Projected Image Refinement in 3D Gaussian Splatting (AAAI 2026 · better on 8 of 8 shared results)
- Semantic Foam: Unifying Spatial and Semantic Scene Decomposition (CVPR 2026 · better on 4 of 6 shared results)
- LangSurf: Language-Embedded Surface Gaussians for 3D Scene Understanding (TPAMI 2026 · better on 4 of 4 shared results)
- IQGS: Instance Query-based Gaussian Segmentation (AAAI 2026 · better on 3 of 3 shared results)
- ID-Splat: Propagating Object Identities for Segmenting 3D Aerial-view Scenes (AAAI 2026 · better on 3 of 3 shared results)
- WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes (NeurIPS 2026 · better on 2 of 2 shared results)
11 more not listed.
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- LangSplat — LangSplat: 3D Language Gaussian Splatting (CVPR 2024) · better on 2 of 2 shared results
- LERF — LERF: Language Embedded Radiance Fields (ICCV 2023) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting (NeurIPS 2024 · similarity 0.90)
- Textured Gaussians for Enhanced 3D Scene Appearance Modeling (CVPR 2025 · similarity 0.90)
- GaussianSpa: An "Optimizing-Sparsifying" Simplification Framework for Compact and High-Quality 3D Gaussian Splatting (CVPR 2025 · similarity 0.90)
- SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering (CVPR 2024 · similarity 0.89)
- Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives (CVPR 2025 · similarity 0.89)
- Optimized Minimal 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
