Research map / 3D vision / Human pose estimation
Convolutional Cross-View Pose Estimation
Zimin Xia, Olaf Booij, Julian F. P. Kooij
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 VGG backbone with EfficientNet-B0 | CVR · VIGOR Same-Area (known orientation) | localization error (m): 7.68 -> 6.25 median | Improved |
| use CCVPE instead of SliceMatch | SliceMatch · VIGOR Same-Area (unknown orientation) | median localization error (m): 5.07 -> 1.42 | Improved |
| use CCVPE instead of SliceMatch | SliceMatch · VIGOR Same-Area (unknown orientation) | median orientation error (deg): 5.15 -> 6.62 | Hurt |
| use CCVPE instead of SliceMatch | SliceMatch · VIGOR Cross-Area (unknown orientation) | median localization error (m): 5.64 -> 1.89 | Improved |
| use CCVPE instead of SliceMatch | SliceMatch · VIGOR Cross-Area (unknown orientation) | median orientation error (deg): 5.18 -> 13.58 | Hurt |
| use CCVPE instead of SliceMatch | SliceMatch · KITTI Same-Area (+-10 deg orientation prior) | median localization error (m): 4.39 -> 0.62 | Improved |
| use CCVPE instead of SliceMatch | SliceMatch · KITTI Same-Area (unknown orientation) | median orientation error (deg): 4.42 -> 6.12 | Hurt |
| use CCVPE instead of SliceMatch | SliceMatch · KITTI Cross-Area (+-10 deg orientation prior) | median localization error (m): 9.77 -> 3.33 | Improved |
| use CCVPE instead of SliceMatch | SliceMatch · KITTI Cross-Area (unknown orientation) | median localization error (m): 11.85 -> 10.98 | Improved |
| remove orientation prior at test time | LM · KITTI Same-Area | median orientation error (deg): 2.83 -> 90.75 | Hurt |
| test on unseen areas instead of same areas | CCVPE · VIGOR (known orientation) | median localization error (m): 1.36 -> 1.68 | Hurt |
| provide known orientation vs unknown orientation | CCVPE · VIGOR Same-Area | median localization error (m): 1.36 -> 1.42 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SliceMatch — SliceMatch: Geometry-Guided Aggregation for Cross-View Pose Estimation (CVPR 2023) · better on 12 of 15 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SliceMatch: Geometry-Guided Aggregation for Cross-View Pose Estimation (CVPR 2023 · similarity 0.92)
- View From Above: Orthogonal-View aware Cross-view Localization (CVPR 2024 · similarity 0.90)
- FG^2: Fine-Grained Cross-View Localization by Fine-Grained Feature Matching (CVPR 2025 · similarity 0.89)
- Seeing Across Skies and Streets: Feedforward 3D Reconstruction from Satellite, Drone, and Ground Images (NeurIPS 2026 · similarity 0.88)
- BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization (NeurIPS 2025 · similarity 0.88)
- PIDLoc: Cross-View Pose Optimization Network Inspired by PID Controllers (CVPR 2025 · 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.
