mlsanityData to 7 Oct 2026

SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM

arXiv 2603.21055 ↗First posted 22 Mar 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

3D Gaussian Splatting (3DGS) has made remarkable progress in RGBD SLAM. Current methods usually use 3D Gaussians or view-tied 3D Gaussians to represent radiance fields in tracking and mapping. However, these Gaussians are either too flexible or too limited in movements, resulting in slow convergence or limited rendering quality. To resolve this issue, we adopt pixel-aligned Gaussians but allow each Gaussian to adjust its position along its ray to maximize the rendering quality, even if Gaussians are simplified to improve system scalability. To speed up the tracking, we model the depth distribution around each pixel as a Gaussian distribution, and then use these distributions to align each frame to the 3D scene quickly. We report our evaluations on widely used benchmarks, justify our designs, and show advantages over the latest methods in view rendering, camera tracking, runtime, and storage complexity. Please see our project page for code and videos at https://machineperceptionlab.github.io/SGAD-SLAM-Project .

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 82 of its 97 references that are in the map. First posted on arXiv 22 Mar 2026.

Builds on

82 of 97 references.

References · 82

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,698
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,607
  6. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,194
  7. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  8. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  9. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 885
  10. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  11. 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 731
  12. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
38 more
  1. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  2. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  3. 2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 467
  4. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 386
  5. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 359
  6. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  7. 2021Neural RGB-D Surface Reconstructioncited by 312
  8. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 298
  9. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 280
  10. 2023GS-SLAM: Dense Visual SLAM with 3D Gaussian Splattingcited by 278
  11. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  12. 2024Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenescited by 226
  13. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 198
  14. 2023Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAMcited by 183
  15. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 161
  16. 2023Point-SLAM: Dense Neural Point Cloud-based SLAMcited by 160
  17. 2022ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fieldscited by 158
  18. 2021Vision-Only Robot Navigation in a Neural Radiance Worldcited by 153
  19. 2023Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splattingcited by 152
  20. 2022Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representationcited by 149
  21. 2023Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Camerascited by 139
  22. 20243D Gaussian Ray Tracing: Fast Tracing of Particle Scenescited by 138
  23. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 132
  24. 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifoldcited by 130
  25. 2022NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priorscited by 125
  26. 2022Neural 3D Scene Reconstruction with the Manhattan-world Assumptioncited by 123
  27. 2021TransformerFusion: Monocular RGB Scene Reconstruction using Transformerscited by 107
  28. 2024SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videoscited by 100
  29. 2023vMAP: Vectorised Object Mapping for Neural Field SLAMcited by 67
  30. 2024GS2Mesh: Surface Reconstruction from Gaussian Splatting via Novel Stereo Viewscited by 65
  31. 2024Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussianscited by 64
  32. 2022GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstructioncited by 61
  33. 2024CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Fieldcited by 61
  34. 2024LoopSplat: Loop Closure by Registering 3D Gaussian Splatscited by 59
  35. 2024Loopy-SLAM: Dense Neural SLAM with Loop Closurescited by 48
  36. 2024Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Setcited by 47
  37. 2024Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesiscited by 41
  38. 2024Human Hair Reconstruction with Strand-Aligned 3D Gaussianscited by 35

50 most cited of 82 All 82 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Dual Covariance Gaussian Splatting SLAM: Decoupling Rendering and Registration for Robust Real-Time Trackingcited by 0