Research map / 3D vision / Human pose estimation
Cov2Pose: Leveraging Spatial Covariance for Direct Manifold-aware 6-DoF Object Pose Estimation
Nassim Ali Ousalah, Peyman Rostami, Vincent Gaudillière, Emmanuel Koumandakis, Anis Kacem, Enjie Ghorbel, Djamila Aouada
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 |
|---|---|---|---|
| use SPD manifold head instead of Euclidean MLP head (ablation) | Cov2Pose · LM-O | ADD(-S): 31.0 -> 76.8 | Improved |
| use spatial covariance instead of channel covariance (ablation) | Cov2Pose · LM-O | ADD(-S): 70.9 -> 76.8 | Improved |
| add Cholesky pose decoding with SO(3) loss instead of log-tangent-space training (ablation) | Cov2Pose · LM-O | ADD(-S): 72.3 -> 76.8 | Improved |
| use 6D rotation with Gram-Schmidt (4x4 SPD) instead of Euler angles (3x3 SPD) (ablation) | Cov2Pose · LM-O | ADD(-S): 70.9 -> 76.8 | Improved |
| Cov2Pose vs indirect PnP methods | Cov2Pose · LM | ADD(-S): 97.1 -> 97.2 | No clear effect |
| Cov2Pose vs ZebraPose on occlusion | Cov2Pose · LM-O | ADD(-S): 76.9 -> 76.8 | No clear effect |
| Cov2Pose vs GDR-Net on YCB-V AUC | Cov2Pose · YCB-V | AUC of ADD(-S): 84.4 -> 82.2 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- GDR-Net — GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation (CVPR 2021) · better on 3 of 5 shared results
- EPro-PnP — EPro-PnP: Generalized End-to-End Probabilistic Perspective-N-Points for Monocular Object Pose Estimation (CVPR 2022) · better on 1 of 1 shared result
- ZebraPose — ZebraPose: Coarse To Fine Surface Encoding for 6DoF Object Pose Estimation (CVPR 2022) · better on 1 of 1 shared result
- Self6D++ — Self6D: Self-Supervised Monocular 6D Object Pose Estimation (ECCV 2020) · 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
- Co-op: Correspondence-based Novel Object Pose Estimation (CVPR 2025 · similarity 0.88)
- GPV-Pose: Category-Level Object Pose Estimation via Geometry-Guided Point-Wise Voting (CVPR 2022 · similarity 0.87)
- F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation (NeurIPS 2026 · similarity 0.87)
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.86)
- GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation (CVPR 2025 · similarity 0.86)
- SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation (CVPR 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.
