Research map / 3D vision / Gaussian splatting
MBA-SLAM: Motion Blur Aware Dense Visual SLAM With Radiance Fields Representation
Peng Wang, Lingzhe Zhao, Yin Zhang, Shiyu Zhao, Peidong Liu
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 |
|---|---|---|---|
| use 3D Gaussian Splatting mapper instead of tri-plane NeRF mapper | MBA-SLAM · ArchViz (synthetic blur) | ATE RMSE avg (cm): 1.69 -> 0.84 | Improved |
| use 3D Gaussian Splatting mapper instead of tri-plane NeRF mapper | MBA-SLAM · ArchViz (synthetic blur) | PSNR avg: 25.08 -> 28.82 | Improved |
| use 3D Gaussian Splatting mapper instead of tri-plane NeRF mapper | MBA-SLAM · Replica (sharp) | PSNR avg: 30.85 -> 36.98 | Improved |
| use 3D Gaussian Splatting mapper instead of tri-plane NeRF mapper | MBA-SLAM · Replica (sharp) | FPS: 2.75 -> 497.63 | Improved |
| replace vanilla NeRF with tri-plane representation | BAD-NeRF based mapper · training efficiency | training speed: 100 times | Improved |
| blur-aware tracker plus mapper vs MonoGS | MBA-SLAM (Ours-GS) · ArchViz (synthetic blur) | ATE RMSE avg (cm): 14.42 -> 0.84 | Improved |
| blur-aware tracker plus mapper vs Photo-SLAM on real blur | MBA-SLAM (Ours-GS) · Realsense blurred sequences (seq1-3) | ATE RMSE avg (cm): 35.81 -> 5.87 | Improved |
| blur-aware NeRF tracker vs ESLAM on real blur | MBA-SLAM (Ours-NeRF) · TUM/ScanNet blurred sequences (pub1-3) | ATE RMSE avg (cm): 2.81 -> 2.34 | Improved |
| MBA-SLAM NeRF vs Point-SLAM on sharp Replica tracking | MBA-SLAM (Ours-NeRF) · Replica (sharp) | ATE RMSE avg (cm): 0.54 -> 0.41 | Improved |
| MBA-SLAM NeRF vs Point-SLAM on sharp Replica rendering | MBA-SLAM (Ours-NeRF) · Replica (sharp) | PSNR avg: 35.05 -> 30.85 | Hurt |
| MBA-SLAM GS vs RTG-SLAM on sharp Replica tracking | MBA-SLAM (Ours-GS) · Replica (sharp) | ATE RMSE avg (cm): 0.18 -> 0.35 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- Photo-SLAM — Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras (CVPR 2024) · better on 4 of 4 shared results
- CoSLAM — Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM (CVPR 2023) · better on 3 of 3 shared results
- ESLAM — ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields (CVPR 2023) · better on 2 of 2 shared results
- SplaTAM — SplaTAM: Splat Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024) · better on 1 of 1 shared result
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
- GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting (CVPR 2024 · similarity 0.89)
- DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization (NeurIPS 2024 · similarity 0.89)
- IBD-SLAM: Learning Image-Based Depth Fusion for Generalizable SLAM (CVPR 2024 · similarity 0.89)
- VTGaussian-SLAM: RGBD SLAM for Large Scale Scenes with Splatting View-Tied 3D Gaussians (ICML 2025 · similarity 0.89)
- Gaussian Splatting SLAM (CVPR 2024 · similarity 0.89)
- Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras (CVPR 2024 · similarity 0.88)
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.
