Research map / Point clouds / Point cloud classification
Paired-Point Lifting for Enhanced Privacy-Preserving Visual Localization
Chunghwan Lee, Jaihoon Kim, Chanhyuk Yun, Je Hyeong Hong
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 |
|---|---|---|---|
| replace standard lifting with paired-point lifting | visual localization line clouds · Energy Landscape | PSNR: 13.30 -> 10.42 | Improved |
| replace standard lifting with paired-point lifting | visual localization line clouds · Cambridge Landmarks | PSNR: 12.67 -> 11.20 | Improved |
| replace OLC with PPL | visual localization · Energy Landscape | median rotation error: 0.104 -> 0.112 | No clear effect |
| replace OLC with PPL | visual localization · Cambridge Landmarks | median rotation error: 0.100 -> 0.200 | No clear effect |
| add rejection of lines nearly parallel to local planes (ablation) | PPL · Energy Landscape | PSNR: 10.42 -> 11.21 | Hurt |
| add rejection of lines nearly parallel to local planes (ablation) | PPL · Cambridge Landmarks | PSNR: 11.20 -> 11.43 | Hurt |
| use two-peak finding instead of single-peak finding (ablation) | PPL · Energy Landscape | median 3D point error: 0.056 -> 0.227 | Hurt |
| use two-peak finding instead of single-peak finding (ablation) | PPL · Cambridge Landmarks | median 3D point error: 0.973 -> 2.845 | Hurt |
| reduce OLC line-cloud density from 100% to 50% (ablation) | OLC · Energy Landscape | PSNR: 13.30 -> 12.84 | Improved |
| reduce OLC line-cloud density from 100% to 50% (ablation) | OLC · Cambridge Landmarks | PSNR: 12.67 -> 12.40 | Improved |
Closest papers by meaning
- Efficient Privacy-Preserving Visual Localization Using 3D Ray Clouds (CVPR 2024 · similarity 0.92)
- Gaussian Splatting Feature Fields for (Privacy-Preserving) Visual Localization (CVPR 2025 · similarity 0.88)
- Toward Availability Attacks in 3D Point Clouds (ICML 2024 · similarity 0.85)
- ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud Restoration (ICLR 2025 · similarity 0.85)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · similarity 0.85)
- Explicitly Perceiving and Preserving the Local Geometric Structures for 3D Point Cloud Attack (AAAI 2024 · similarity 0.85)
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.
