Research map / Point clouds / Registration and matching
PGCR: Pose–Geometry Coupled Reasoning for Image-to-Point Cloud Registration
Xinjun Li, Wenfei Yang, Yihan Chen, Zhixin Cheng, Shifeng Zhang, Xu Zhou, Tianzhu Zhang
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 Geometry-aware Pose Refinement (ablation) | PGCR · KITTI | RTE (m): 0.17 -> 0.15 | Improved |
| add Geometry-aware Pose Refinement (ablation) | PGCR · KITTI | RRE (deg): 0.49 -> 0.44 | Improved |
| add Geometry-aware Pose Refinement (ablation) | PGCR · nuScenes | RTE (m): 0.50 -> 0.43 | Improved |
| add Geometry-aware Pose Refinement (ablation) | PGCR · nuScenes | RRE (deg): 1.06 -> 0.88 | Improved |
| add Pose-guided Progressive Refinement (full) (ablation) | PGCR · KITTI | RTE (m): 0.33 -> 0.17 | Improved |
| add Pose-guided Progressive Refinement (full) (ablation) | PGCR · KITTI | RRE (deg): 0.94 -> 0.49 | Improved |
| add Pose-guided Progressive Refinement (full) (ablation) | PGCR · nuScenes | RTE (m): 0.74 -> 0.50 | Improved |
| add pose-guided filter on top of intermediate supervision (stage 4) (ablation) | PGCR · KITTI | RTE (m): 0.25 -> 0.17 | Improved |
| add intermediate supervision only (stage 4, no filter) (ablation) | PGCR · KITTI | RTE (m): 0.33 -> 0.25 | Improved |
| add depth supervision only (ablation) | PGCR · KITTI | RTE (m): 0.21 -> 0.18 | Improved |
| add point map supervision only (ablation) | PGCR · KITTI | RTE (m): 0.21 -> 0.20 | Improved |
| add both depth and point map supervision (ablation) | PGCR · nuScenes | RRE (deg): 1.44 -> 1.06 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- GraphI2P — GraphI2P: Image-to-Point Cloud Registration with Exploring Pattern of Correspondence via Graph Learning (CVPR 2025) · better on 6 of 6 shared results
- CA-I2P — CA-I2P: Channel-Adaptive Registration Network with Global Optimal Selection (ICCV 2025) · better on 4 of 4 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
- RayI2P: Learning Rays for Image-to-Point Cloud Registration (ICLR 2026 · similarity 0.89)
- $\pi^2$: A Simple Framework for 2D-to-3D Registration (NeurIPS 2026 · similarity 0.89)
- Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching (ECCV 2026 · similarity 0.89)
- Implicit Correspondence Learning for Image-to-Point Cloud Registration (CVPR 2025 · similarity 0.88)
- Rectified Point Flow: Generic Point Cloud Pose Estimation (NeurIPS 2025 · similarity 0.87)
- 3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration (NeurIPS 2024 · 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.
