Research map / Federated learning and privacy / Differential privacy
Privacy Preserving Localization via Coordinate Permutations
Linfei Pan, Johannes L. Schönberger, Viktor Larsson, Marc Pollefeys
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 random line lifting with coordinate permutation plus point recovery | private-query localization · HoloLens (private query) | AUC@(1deg,10cm): 97.80 -> 98.41 | Improved |
| replace random line lifting with coordinate permutation plus point recovery | private-query localization · Cambridge (private query) | AUC@(1deg,10cm): 41.29 -> 44.26 | Improved |
| replace random 3D line lifting with 3D coordinate permutation | private-map localization · HoloLens (private map) | AUC@(1deg,10cm): 97.71 -> 97.92 | Improved |
| replace random line lifting with coordinate permutation | private-query localization · HoloLens / Cambridge / Internet photos | runtime (s): 0.07 -> 0.36 (HoloLens); 0.36 -> 2.31 (Cambridge) | Hurt |
| add recovered 2D point constraints on top of line constraints only (ablation) | coordinate permutation localization · HoloLens | accuracy | Improved |
| use point recovery instead of oracle with ground truth points (ablation) | coordinate permutation localization · HoloLens | accuracy | No clear effect |
| use axis-aligned permuted lines instead of random line cloud against density attack | private map · Line2Point inversion attack | recognizability of inverted images | Improved |
Closest papers by meaning
- Privacy Preserving Partial Localization (CVPR 2022 · similarity 0.93)
- Privacy Preserving Structure-from-Motion (ECCV 2020 · similarity 0.92)
- Privacy Preserving Image-Based Localization (CVPR 2019 · similarity 0.92)
- Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image Queries in Visual Localization (CVPR 2026 · similarity 0.92)
- Efficient Privacy-Preserving Visual Localization Using 3D Ray Clouds (CVPR 2024 · similarity 0.89)
- Gaussian Splatting Feature Fields for (Privacy-Preserving) Visual Localization (CVPR 2025 · 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.
