mlsanityData to 14 Oct 2026

Deblur Gaussian Splatting SLAM

arXiv 2503.12572 ↗First posted 16 Mar 2025cs.CV cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

We present Deblur-SLAM, a robust RGB SLAM pipeline designed to recover sharp reconstructions from motion-blurred inputs. The proposed method bridges the strengths of both frame-to-frame and frame-to-model approaches to model sub-frame camera trajectories that lead to high-fidelity reconstructions in motion-blurred settings. Moreover, our pipeline incorporates techniques such as online loop closure and global bundle adjustment to achieve a dense and precise global trajectory. We model the physical image formation process of motion-blurred images and minimize the error between the observed blurry images and rendered blurry images obtained by averaging sharp virtual sub-frame images. Additionally, by utilizing a monocular depth estimator alongside the online deformation of Gaussians, we ensure precise mapping and enhanced image deblurring. The proposed SLAM pipeline integrates all these components to improve the results. We achieve state-of-the-art results for sharp map estimation and sub-frame trajectory recovery both on synthetic and real-world blurry input data.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 58 of its 86 references that are in the map. First posted on arXiv 16 Mar 2025.

Builds on

58 of 86 references.

References · 58

  1. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  3. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  5. 2021Vision Transformers for Dense Predictioncited by 1,803
  6. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  7. 2024Depth Anything V2cited by 1,422
  8. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 904
  9. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
  10. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 589
  11. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 511
  12. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
38 more
  1. 2023Gaussian Splatting SLAMcited by 415
  2. 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
  3. 2021Neural RGB-D Surface Reconstructioncited by 313
  4. 2023GS-SLAM: Dense Visual SLAM with 3D Gaussian Splattingcited by 278
  5. 2021NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Videocited by 241
  6. 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
  7. 2023Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAMcited by 184
  8. 2021Deblur-NeRF: Neural Radiance Fields from Blurry Imagescited by 179
  9. 2018BA-Net: Dense Bundle Adjustment Networkcited by 175
  10. 2023Point-SLAM: Dense Neural Point Cloud-based SLAMcited by 160
  11. 2023Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splattingcited by 154
  12. 2022Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representationcited by 149
  13. 2023Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular, Stereo, and RGB-D Camerascited by 141
  14. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 133
  15. 2023Distilled Feature Fields Enable Few-Shot Language-Guided Manipulationcited by 130
  16. 2022iSDF: Real-Time Neural Signed Distance Fields for Robot Perceptioncited by 109
  17. 2021TransformerFusion: Monocular RGB Scene Reconstruction using Transformerscited by 106
  18. 2022BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fieldscited by 80
  19. 2022Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mappingcited by 79
  20. 2024How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Surveycited by 72
  21. 2024Deblurring 3D Gaussian Splattingcited by 66
  22. 2024Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussianscited by 66
  23. 2024BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splattingcited by 61
  24. 2020RoutedFusion: Learning Real-time Depth Map Fusioncited by 52
  25. 2024Loopy-SLAM: Dense Neural SLAM with Loop Closurescited by 48
  26. 2020NeuralFusion: Online Depth Fusion in Latent Spacecited by 46
  27. 2024GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAMcited by 36
  28. 2023CP-SLAM: Collaborative Neural Point-based SLAM Systemcited by 32
  29. 2023HI-SLAM: Monocular Real-time Dense Mapping with Hybrid Implicit Fieldscited by 31
  30. 2022BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusioncited by 29
  31. 2024Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motioncited by 29
  32. 2020Voxgraph: Globally Consistent, Volumetric Mapping using Signed Distance Function Submapscited by 26
  33. 2023MIPS-Fusion: Multi-Implicit-Submaps for Scalable and Robust Online Neural RGB-D Reconstructioncited by 24
  34. 2023UncLe-SLAM: Uncertainty Learning for Dense Neural SLAMcited by 19
  35. 2023Hybrid Neural Rendering for Large-Scale Scenes with Motion Blurcited by 18
  36. 2022FD-SLAM: 3-D Reconstruction Using Features and Dense Matchingcited by 17
  37. 2022MonoNeuralFusion: Online Monocular Neural 3D Reconstruction with Geometric Priorscited by 17
  38. 2023NEWTON: Neural View-Centric Mapping for On-the-Fly Large-Scale SLAMcited by 17

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Towards Next-Generation SLAM: A Survey on 3DGS-SLAM Focusing on Performance, Robustness, and Future Directionscited by 2
  2. 2026Unblur-SLAM: Dense Neural SLAM for Blurry Inputscited by 1