Research map / 3D vision / Human pose estimation
VIRD: View-Invariant Representation through Dual-Axis Transformation for Cross-View Pose Estimation
Juhye Park, Wooju Lee, Dasol Hong, Changki Sung, Youngwoo Seo, Dongwan Kang, Hyun Myung
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 |
|---|---|---|---|
| add positional attention after polar transform (ablation) | polar-transformed VIRD · KITTI cross-area (VGG16) | median position error (m): 11.75 -> 9.76 | Improved |
| add context enhancement to positional attention (CEPA) (ablation) | VIRD · KITTI cross-area (VGG16) | median position error (m): 9.76 -> 8.88 | Improved |
| replace projective transforms with polar + CEPA (ablation) | VIRD · KITTI cross-area (VGG16) | median position error (m): 10.59 -> 8.88 | Improved |
| add original-view reconstruction loss (ablation) | VIRD · KITTI cross-area (VGG16) | mean orientation error (deg): 31.35 -> 28.26 | Improved |
| add cross-view reconstruction loss (ablation) | VIRD · KITTI cross-area (VGG16) | mean orientation error (deg): 31.35 -> 26.30 | Improved |
| add both reconstruction losses (ablation) | VIRD · KITTI cross-area (VGG16) | mean orientation error (deg): 31.35 -> 21.91 | Improved |
| add regression module (ablation) | VIRD · KITTI cross-area (VGG16) | median position error (m): 7.90 -> 7.05 | Improved |
| add regression module (ablation) | VIRD · KITTI cross-area (VGG16) | mean orientation error (deg): 21.91 -> 25.10 | Hurt |
| add regression module (ablation) | VIRD · KITTI cross-area (VGG16) | median orientation error (deg): 3.05 -> 2.22 | Improved |
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 2 of 2 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
- Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer (ICCV 2023 · similarity 0.91)
- 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)
- View From Above: Orthogonal-View aware Cross-view Localization (CVPR 2024 · similarity 0.87)
- Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery (NeurIPS 2026 · similarity 0.86)
- PIDLoc: Cross-View Pose Optimization Network Inspired by PID Controllers (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.
