GLS: Geometry-aware 3D Language Gaussian Splatting
Not on the map. Why?
Abstract (arXiv)
Recently, 3D Gaussian Splatting (3DGS) has achieved impressive performance on indoor surface reconstruction and 3D open-vocabulary segmentation. This paper presents GLS, a unified framework of 3D surface reconstruction and open-vocabulary segmentation based on 3DGS. GLS extends two fields by improving their sharpness and smoothness. For indoor surface reconstruction, we introduce surface normal prior as a geometric cue to guide the rendered normal, and use the normal error to optimize the rendered depth. For 3D open-vocabulary segmentation, we employ 2D CLIP features to guide instance features and enhance the surface smoothness, then utilize DEVA masks to maintain their view consistency. Extensive experiments demonstrate the effectiveness of jointly optimizing surface reconstruction and 3D open-vocabulary segmentation, where GLS surpasses state-of-the-art approaches of each task on MuSHRoom, ScanNet++ and LERF-OVS datasets. Project webpage: https://jiaxiongq.github.io/GLS_ProjectPage.
Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 45 of its 65 references that are in the map. First posted on arXiv 27 Nov 2024.
Builds on
45 of 65 references.
References · 45
- 2023GPT-4 Technical Reportcited by 18,396
- 2023Segment Anythingcited by 8,234
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
- 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
- 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
- 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
- 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
- 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
33 more
- 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
- 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
- 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
- 2023LERF: Language Embedded Radiance Fieldscited by 543
- 2023LangSplat: 3D Language Gaussian Splattingcited by 415
- 2023Gaussian Grouping: Segment and Edit Anything in 3D Scenescited by 393
- 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 364
- 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 311
- 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 286
- 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 285
- 2019Differentiable Surface Splatting for Point-based Geometry Processingcited by 239
- 2024Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenescited by 232
- 2023MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenescited by 218
- 2023Language Embedded 3D Gaussians for Open-Vocabulary Scene Understandingcited by 208
- 2023ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understandingcited by 202
- 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagationcited by 200
- 2022PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learningcited by 187
- 2024VR-GS: A Physical Dynamics-Aware Interactive Gaussian Splatting System in Virtual Realitycited by 179
- 2022CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingcited by 160
- 2024OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understandingcited by 145
- 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 138
- 2024Rethinking Inductive Biases for Surface Normal Estimationcited by 124
- 2024RaDe-GS: Rasterizing Depth in Gaussian Splattingcited by 111
- 2024Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splattingcited by 82
- 2022Object-Compositional Neural Implicit Surfacescited by 74
- 2024Analytic-Splatting: Anti-Aliased 3D Gaussian Splatting via Analytic Integrationcited by 67
- 2024VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstructioncited by 50
- 2024Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Setcited by 49
- 2023ObjectSDF++: Improved Object-Compositional Neural Implicit Surfacescited by 39
- 2021Differentiable Stereopsis: Meshes from multiple views using differentiable renderingcited by 26
- 2024Radiance Fields for Robotic Teleoperationcited by 13
- 2023MuSHRoom: Multi-Sensor Hybrid Room Dataset for Joint 3D Reconstruction and Novel View Synthesiscited by 12
- 2024GSLoc: Visual Localization with 3D Gaussian Splattingcited by 12
Built on by
Citing papers per year: 2025: 8; 2026: 1.
9 papers.
- 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
- 2025VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understandingcited by 11
- 2025Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Fieldcited by 7
- 2025MMOne: Representing Multiple Modalities in One Scenecited by 3
- 2025SAGOnline: Segment Any Gaussians Onlinecited by 3
- 2025DSG-World: Learning a 3D Gaussian World Model from Dual State Videoscited by 1
- 2025PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priorscited by 1
- 2025OGGSplat: Open Gaussian Growing for Generalizable Reconstruction with Expanded Field-of-Viewcited by 0
- 2026RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videoscited by 0
- 2026RoSe-SLAM: Robust Semantic-Aware Gaussian Splatting SLAM from Dynamic Monocular Videos29 Aug 2026
- 2025PlanarGS: High-Fidelity Indoor 3D Gaussian Splatting Guided by Vision-Language Planar Priors27 Oct 2025
- 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation13 Aug 2025
- 2025SAGOnline: Segment Any Gaussians Online11 Aug 2025
- 2025MMOne: Representing Multiple Modalities in One Scene15 Jul 2025
- 2025VoteSplat: Hough Voting Gaussian Splatting for 3D Scene Understanding28 Jun 2025
- 2025DSG-World: Learning a 3D Gaussian World Model from Dual State Videos5 Jun 2025
- 2025OGGSplat: Open Gaussian Growing for Generalizable Reconstruction with Expanded Field-of-View5 Jun 2025
- 2025Pointmap Association and Piecewise-Plane Constraint for Consistent and Compact 3D Gaussian Segmentation Field22 Feb 2025