Research map / 3D vision / Human pose estimation
DCL-Net: Deep Correspondence Learning Network for 6D Pose Estimation
Hongyang Li, Jiehong Lin, Kui Jia
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 P2P-FDA module (ablation) | DCL-Net · YCB-Video ablation (no confidence, no refinement) | ADD-S AUC: 94.1 -> 95.0 | Improved |
| add C2C-FDA module (ablation) | DCL-Net · YCB-Video ablation (no confidence, no refinement) | ADD-S AUC: 94.1 -> 94.5 | Improved |
| add C2C-FDA to P2P-FDA (dual modules) (ablation) | DCL-Net · YCB-Video ablation (no confidence, no refinement) | ADD-S AUC: 95.0 -> 95.3 | Improved |
| add P2P-FDA to C2C-FDA (dual modules) (ablation) | DCL-Net · YCB-Video ablation (no confidence, no refinement) | ADD-S AUC: 94.5 -> 95.3 | Improved |
| add dual FDA modules (ablation) | DCL-Net · YCB-Video ablation (no confidence, no refinement) | ADD-S <2cm: 97.4 -> 99.0 | Improved |
| use P2P-FDA instead of C2C-FDA (ablation) | DCL-Net · YCB-Video ablation (no confidence, no refinement) | CD (x10^-3): 7.1 -> 8.2 | Improved |
| use direct pose regression instead of least-squares optimization (no confidence) (ablation) | DCL-Net · YCB-Video ablation (no refinement) | ADD-S AUC: 94.7 -> 95.3 | Improved |
| use direct pose regression instead of least-squares optimization (with confidence) (ablation) | DCL-Net · YCB-Video ablation (no refinement) | ADD-S AUC: 95.4 -> 95.8 | Improved |
| add confidence weighting to direct pose regression (ablation) | DCL-Net · YCB-Video ablation (no refinement) | ADD-S AUC: 95.3 -> 95.8 | Improved |
| add confidence weighting to least-squares optimization (ablation) | DCL-Net · YCB-Video ablation (no refinement) | ADD-S AUC: 94.7 -> 95.4 | Improved |
| add confidence-based pose refinement (ablation) | DCL-Net · YCB-Video | ADD-S AUC: 95.8 -> 96.6 | Improved |
| add confidence-based pose refinement (ablation) | DCL-Net · YCB-Video | ADD-S <2cm: 99.0 -> 99.0 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 on most shared results.
- PR-GCN — PR-GCN: A Deep Graph Convolutional Network With Point Refinement for 6D Pose Estimation (ICCV 2021) · better on 4 of 4 shared results
- PVN3D — PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation (CVPR 2020) · better on 3 of 3 shared results
- DenseFusion — DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion (CVPR 2019) · better on 3 of 3 shared results
- PVNet — PVNet: Pixel-Wise Voting Network for 6DoF Pose Estimation (CVPR 2019) · better on 1 of 1 shared result
- 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
- Single-Stage 6D Object Pose Estimation (CVPR 2020 · similarity 0.91)
- DeepIM: Deep Iterative Matching for 6D Pose Estimation (ECCV 2018 · similarity 0.91)
- DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-Scale Consistency (CVPR 2021 · similarity 0.90)
- GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation (CVPR 2021 · similarity 0.89)
- FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects (CVPR 2024 · similarity 0.87)
- Co-op: Correspondence-based Novel Object Pose Estimation (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.
