Research map / Federated learning and privacy / Privacy attacks and secure learning
Privacy Preserving Partial Localization
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 parallel-plane partial maps instead of point-to-point alignment | Localization on Alamo · Alamo | Recall at τ2 (0.2m / 5°): 60.8 -> 62.6 | Helped |
| Use parallel-plane partial maps instead of point-to-point alignment | Localization on Gendarmenmarkt · Gendarmenmarkt | Recall at τ2 (0.2m / 5°): 40.8 -> 31.1 | Hurt |
| Use parallel-plane partial maps instead of point-to-point alignment | Localization on Madrid Metropolis · Madrid Metropolis | Recall at τ2 (0.2m / 5°): 32.1 -> 36.1 | Helped |
| Use parallel-plane partial maps instead of point-to-point alignment | Localization on Roman Forum · Roman Forum | Recall at τ2 (0.2m / 5°): 53.0 -> 43.8 | Hurt |
| Use parallel-plane partial maps instead of point-to-point alignment | Localization on Tower of London · Tower of London | Recall at τ2 (0.2m / 5°): 43.7 -> 37.1 | Hurt |
| Use parallel-plane partial maps instead of point-to-point alignment | Localization on Aachen · Aachen | Recall at τ2 (0.2m / 5°): 76.4 -> 57.9 | Hurt |
| Use parallel-plane partial maps instead of point-to-point alignment | Localization on Dubrovnik · Dubrovnik | Recall at τ2 (0.2m / 5°): 35.3 -> 24.0 | Hurt |
| Use parallel-plane partial maps instead of point-to-point alignment | Localization on chess · chess | Recall at τ2 (0.2m / 5°): 99.5 -> 97.5 | Hurt |
| Use parallel-plane partial maps instead of point-to-point alignment | Localization on fire · fire | Recall at τ2 (0.2m / 5°): 99.5 -> 97.0 | Hurt |
| Use parallel-plane partial maps instead of point-to-plane alignment | Localization on heads · heads | Recall at τ2 (0.2m / 5°): 80.0 -> 77.0 | Hurt |
| Use parallel-plane partial maps instead of point-to-point alignment | Localization on office · office | Recall at τ2 (0.2m / 5°): 64.8 -> 59.0 | Hurt |
| Use parallel-plane partial maps instead of point-to-plane alignment | Localization on pumpkin · pumpkin | Recall at τ2 (0.2m / 5°): 53.0 -> 51.0 | Hurt |
Closest papers by meaning
- Privacy Preserving Image-Based Localization (CVPR 2019 · similarity 0.91)
- 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 0.84)
- Validating Privacy-Preserving Face Recognition under a Minimum Assumption (CVPR 2024 · similarity 0.81)
- ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation (NeurIPS 2025 · similarity 0.81)
- Reconstruction and Secrecy under Approximate Distance Queries (NeurIPS 2025 · similarity 0.80)
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.