Research map / 3D vision / Human pose estimation
Self-Supervised Category-Level 6D Object Pose Estimation with Deep Implicit Shape Representation
Wanli Peng, Jianhang Yan, Hongtao Wen, Yi Sun
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 self-supervised training on real data (ablation) | Ours · NOCS-REAL test | 10°10cm mAP (%): 9.15 -> 49.80 | Improved |
| Add image-flip data augmentation (ablation) | Self-Sup · NOCS-REAL test | 10°10cm mAP (%): 49.80 -> 56.24 | Improved |
| Add chamfer loss (ablation) | Self-supervised framework · NOCS-REAL test | IoU50 mAP (%): 15.31 -> 19.62 | Improved |
| Add SDF alignment loss (ablation) | Self-supervised framework · NOCS-REAL test | IoU50 mAP (%): 13.81 -> 19.62 | Improved |
| Retain supervised synthetic-data loss during joint learning (ablation) | Self-supervised framework · NOCS-REAL test | IoU50 mAP (%): 11.70 -> 19.62 | Improved |
| Add ICP refinement | Ours · NOCS-REAL test | 5°2cm mAP (%): 16.76 -> 28.60 | Improved |
| Add ICP refinement | Ours · NOCS-REAL test | IoU50 mAP (%): 72.95 -> 72.67 | Hurt |
| Use the proposed self-supervised framework instead of NOCS | NOCS-REAL test · NOCS-REAL test | IoU50 mAP (%): 47.23 -> 72.95 | Improved |
Closest papers by meaning
- Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild (ICLR 2023 · similarity 0.92)
- Self6D: Self-Supervised Monocular 6D Object Pose Estimation (ECCV 2020 · similarity 0.91)
- Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation (TPAMI 2021 · similarity 0.89)
- Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimation (ICCV 2023 · similarity 0.89)
- Category-Level 6D Object Pose and Size Estimation Using Self-Supervised Deep Prior Deformation Networks (ECCV 2022 · similarity 0.89)
- Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset (NeurIPS 2022 · similarity 0.88)
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.
