Research map / Point clouds / Point cloud classification
PointSLAM++: Robust Dense Neural Gaussian Point Cloud-based SLAM
Xu Wang, Boyao Han, Xiaojun Chen, Ying Liu, Ruihui Li
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 progressive pose optimization (GICP+ORB+BA) over GICP only (ablation) | PointSLAM++ · TUM-RGBD | ATE RMSE: 17.33 -> 1.08 | Improved |
| add progressive pose optimization (ablation) | PointSLAM++ · TUM-RGBD | PSNR: 21.47 -> 26.16 | Improved |
| add neural Gaussian representation (ablation) | PointSLAM++ · TUM-RGBD | PSNR: 24.06 -> 25.36 | Improved |
| add view-dependent compensation (ablation) | PointSLAM++ · TUM-RGBD | PSNR: 25.36 -> 26.16 | Improved |
| add view-dependent compensation (ablation) | PointSLAM++ · TUM-RGBD | ATE RMSE: 1.10 -> 1.08 | No clear effect |
| use PointSLAM++ instead of GS-ICP SLAM on noisy-depth data | PointSLAM++ · ScanNet++ | PSNR: 14.94 -> 26.51 | Improved |
| PointSLAM++ vs GS-ICP SLAM tracking on clean-depth Replica | PointSLAM++ · Replica | ATE RMSE: 0.16 -> 0.19 | No clear effect |
| PointSLAM++ vs SplaTAM on TUM-RGBD rendering | PointSLAM++ · TUM-RGBD | SSIM: 0.897 -> 0.885 | Hurt |
| PointSLAM++ vs GS-ICP SLAM on efficiency | PointSLAM++ · ScanNet++ | GPU memory (GB): 9.62 -> 10.11 | Hurt |
Closest papers by meaning
- Benchmarking Implicit Neural Representation and Geometric Rendering in Real-Time RGB-D SLAM (CVPR 2024 · similarity 0.87)
- MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM (CVPR 2025 · similarity 0.87)
- Loopy-SLAM: Dense Neural SLAM with Loop Closures (CVPR 2024 · similarity 0.87)
- Photo-SLAM: Real-time Simultaneous Localization and Photorealistic Mapping for Monocular Stereo and RGB-D Cameras (CVPR 2024 · similarity 0.87)
- GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting (CVPR 2024 · similarity 0.86)
- PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment (CVPR 2024 · similarity 0.86)
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.
