Research map / Point clouds / Point cloud classification
Privacy Preserving Visual SLAM
Mikiya Shibuya, Shinya Sumikura, Ken Sakurada
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 LC-VSLAM tracking instead of per-frame p6L localization | line-cloud localization · CARLA #01 | tracking time per frame (ms): 140.3 -> 31.09 | Improved |
| use LC-VSLAM tracking instead of per-frame p6L localization | line-cloud localization · CARLA #01 | APE translation (m): 0.7815 -> 0.1979 | Improved |
| replace 3D point map with 3D line (privacy) map | LC-VSLAM · CARLA perspective | APE translation (m): 3.290 -> 3.651 | Hurt |
| replace 3D point map with 3D line (privacy) map | LC-VSLAM · KITTI perspective | APE translation (m): 3.801 -> 4.488 | Hurt |
| replace 3D point map with 3D line (privacy) map | LC-VSLAM · CARLA equirectangular | APE translation (m): 3.079 -> 3.075 | No clear effect |
| add pose graph optimization (ablation) | LC-VSLAM · CARLA #10-12 perspective | APE translation (m): 24.06 -> 3.301 | Improved |
| add pose graph optimization (ablation) | LC-VSLAM · CARLA #10-12 equirectangular | APE translation (m): 14.28 -> 9.640 | Improved |
| add global BA on top of PGO (ablation) | LC-VSLAM · CARLA #10-12 perspective | APE translation (m): 3.301 -> 3.018 | Improved |
| add global BA on top of PGO (ablation) | LC-VSLAM · CARLA #10-12 equirectangular | APE translation (m): 9.640 -> 8.320 | Improved |
| add global BA on top of PGO (ablation) | LC-VSLAM · CARLA #10-12 fisheye | APE rotation (deg): 0.8039 -> 0.8525 | Hurt |
| add global BA on top of PGO (ablation) | LC-VSLAM · CARLA #10-12 perspective | APE rotation (deg): 1.151 -> 1.100 | Improved |
Closest papers by meaning
- Privacy Preserving Structure-from-Motion (ECCV 2020 · similarity 0.92)
- Privacy Preserving Partial Localization (CVPR 2022 · similarity 0.90)
- Privacy Preserving Image-Based Localization (CVPR 2019 · similarity 0.90)
- Efficient Privacy-Preserving Visual Localization Using 3D Ray Clouds (CVPR 2024 · similarity 0.89)
- ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud Restoration (ICLR 2025 · similarity 0.81)
- Gaussian Splatting Feature Fields for (Privacy-Preserving) Visual Localization (CVPR 2025 · similarity 0.81)
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.
