Research map / 3D vision / Human pose estimation
Neural Correspondence Field for Object Pose Estimation
Lin Huang, Tomas Hodan, Lingni Ma, Linguang Zhang, Luan Tran, Christopher D. Twigg, Po-Chen Wu, Junsong Yuan, Cem Keskin, Robert Wang
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 |
|---|---|---|---|
| predict 3D-3D correspondences at 3D query points instead of 2D-3D pixel correspondences | NCF vs Baseline-full · YCB-V (pbr) | AR: 37.1 -> 67.3 | Improved |
| predict 3D-3D correspondences at 3D query points instead of 2D-3D pixel correspondences | NCF vs Baseline-full · LM-O (pbr) | AR: 33.9 -> 63.2 | Improved |
| add real training images to synthetic pbr images | NCF · YCB-V | AR: 67.3 -> 77.5 | Improved |
| reduce query point sampling step from 10 mm to 5 mm (ablation) | NCF · YCB-V | AR: 66.8 -> 67.0 | No clear effect |
| enlarge query point sampling step from 10 mm to 20 mm (ablation) | NCF · YCB-V | AR: 66.8 -> 66.2 | No clear effect |
| reduce RANSAC iterations from 200 to 50 (ablation) | NCF · YCB-V | AR: 67.3 -> 66.7 | Hurt |
| reduce RANSAC iterations from 200 to 10 (ablation) | NCF · YCB-V | AR: 67.3 -> 65.1 | Hurt |
| increase RANSAC iterations from 200 to 500 (ablation) | NCF · YCB-V | AR: 67.3 -> 67.3 | No clear effect |
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.
- EPOS — EPOS: Estimating 6D Pose of Objects With Symmetries (CVPR 2020) · better on 2 of 2 shared results
- Pix2Pose — Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation (ICCV 2019) · better on 1 of 1 shared result
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
- FAR: Flexible Accurate and Robust 6DoF Relative Camera Pose Estimation (CVPR 2024 · similarity 0.88)
- Co-op: Correspondence-based Novel Object Pose Estimation (CVPR 2025 · similarity 0.88)
- NOPE: Novel Object Pose Estimation from a Single Image (CVPR 2024 · similarity 0.88)
- HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation (CVPR 2024 · similarity 0.87)
- Pos3R: 6D Pose Estimation for Unseen Objects Made Easy (CVPR 2025 · similarity 0.87)
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 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.
