Research map / 3D vision / 3D generation
Semantic Visual Localization
Johannes L. Schönberger, Marc Pollefeys, Andreas Geiger, Torsten Sattler
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 generative semantic scene-completion descriptors instead of the evaluated geometric shape descriptors | Semantic Visual Localization · KITTI 90° viewpoint localization | localization performance | Improved |
| Add semantic information to the learned descriptors (ablation) | Semantic Visual Localization · KITTI 90° viewpoint localization | localization performance | Improved |
| Accumulate evidence from five consecutive query frames (ablation) | Semantic Visual Localization · KITTI 90° viewpoint localization | localization performance | Improved |
| Use the semantic descriptor instead of the geometric-only descriptor (ablation) | Semantic Visual Localization · KITTI 0° viewpoint localization | localization performance | No clear effect |
| Use the semantic descriptor instead of the geometric-only descriptor (ablation) | Semantic Visual Localization · NCLT cross-time localization | localization performance | Improved |
| Use a latent code size below 64 (ablation) | Semantic Visual Localization · Descriptor learning | reconstruction and localization performance | Hurt |
| Increase latent code size above 512 (ablation) | Semantic Visual Localization · Descriptor learning | reconstruction and localization performance | No clear effect |
| Use SIFT instead of semantic 3D descriptors | Visual localization pipeline · KITTI 90° viewpoint localization | localization performance | Hurt |
| Use multiple accumulated query frames rather than a single-frame query (ablation) | Semantic Visual Localization · Localization across viewpoint and appearance changes | localization performance | Improved |
Closest papers by meaning
- Semantic Match Consistency for Long-Term Visual Localization (ECCV 2018 · similarity 0.90)
- SFD2: Semantic-Guided Feature Detection and Description (CVPR 2023 · similarity 0.89)
- Investigating the Role of Image Retrieval for Visual Localization (IJCV 2022 · similarity 0.88)
- Visual Localization Using Imperfect 3D Models From the Internet (CVPR 2023 · similarity 0.87)
- LOCATE 3D: Real-World Object Localization via Self-Supervised Learning in 3D (ICML 2025 · similarity 0.87)
- Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency (ICLR 2024 · similarity 0.87)
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.
