Research map / 3D vision / Human pose estimation
FS6D: Few-Shot 6D Pose Estimation of Novel Objects
Yisheng He, Yao Wang, Haoqiang Fan, Jian Sun, Qifeng Chen
Check 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 dense RGBD prototype matching with joint appearance and geometric reasoning | FS6D-DPM · YCB-Video | ADDS AUC: 71.0 -> 88.4 | Improved |
| Use dense RGBD prototype matching with joint appearance and geometric reasoning | FS6D-DPM · YCB-Video | ADD AUC: 26.2 -> 42.1 | Improved |
| Use dense RGBD prototype matching with joint appearance and geometric reasoning | FS6D-DPM · LineMOD | ADD-0.1d: 48.0 -> 83.4 | Improved |
| Add online texture blending (ablation) | FS6D-DPM · YCB-Video | ADD: 37.5 -> 60.3 | Improved |
| Pre-train on ShapeNet6D rather than train from scratch (ablation) | FS6D-DPM · LineMOD | ADD-0.1d: 65.2 -> 79.3 | Improved |
| Fine-tune after pre-training on ShapeNet6D (ablation) | FS6D-DPM · LineMOD | ADD-0.1d: 79.3 -> 83.4 | Improved |
| Increase support views from 1 to 4 (ablation) | FS6D-DPM · YCB-Video | ADDS AUC: 79.6 -> 87.3 | Improved |
| Increase support views from 4 to 8 (ablation) | FS6D-DPM · YCB-Video | ADDS AUC: 87.3 -> 87.9 | Improved |
| Increase support views from 8 to 16 (ablation) | FS6D-DPM · YCB-Video | ADDS AUC: 87.9 -> 88.4 | Improved |
| Increase support views from 16 to 32 (ablation) | FS6D-DPM · YCB-Video | ADDS AUC: 88.4 -> 88.6 | Improved |
Closest papers by meaning
- Any6D: Model-free 6D Pose Estimation of Novel Objects (CVPR 2025 · similarity 0.91)
- Omni6D: Large-Vocabulary 3D Object Dataset for Category-Level 6D Object Pose Estimation (ECCV 2024 · similarity 0.91)
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 2025 · similarity 0.90)
- Pos3R: 6D Pose Estimation for Unseen Objects Made Easy (CVPR 2025 · similarity 0.89)
- SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation (CVPR 2024 · similarity 0.89)
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.89)
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.
