Research map / 3D vision / Human pose estimation
DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Replace global fusion-by-concatenation with dense pixel-wise feature fusion (ablation) | DenseFusion · LineMOD | ADD/ADD-S: 73.7 -> 86.2 | Helped |
| Replace global fusion-by-concatenation with dense pixel-wise feature fusion (ablation) | DenseFusion · YCB-Video | ADD-S AUC: 83.9 -> 91.2 | Helped |
| Replace one global-feature pose prediction with per-pixel pose predictions (ablation) | DenseFusion · YCB-Video | ADD-S <2cm: 87.9 -> 95.3 | Helped |
| Add iterative pose refinement (ablation) | DenseFusion (per-pixel) · YCB-Video | ADD-S AUC: 91.2 -> 93.1 | Helped |
| Add iterative pose refinement (ablation) | DenseFusion (per-pixel) · YCB-Video | ADD-S <2cm: 95.3 -> 96.8 | Helped |
| Add iterative pose refinement (ablation) | DenseFusion (per-pixel) · LineMOD | ADD/ADD-S: 86.2 -> 94.3 | Helped |
| Use dense per-pixel predictions and iterative refinement rather than global fusion-by-concatenation | DenseFusion · YCB-Video | ADD-S <2cm: 74.1 -> 96.8 | Helped |
| Use the iterative refinement model instead of PoseCNN+ICP | DenseFusion · YCB-Video | ADD-S <2cm: 93.2 -> 96.8 | Helped |
Closest papers by meaning
- HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimation (CVPR 2024 · similarity 0.87)
- CAP-Net: A Unified Network for 6D Pose and Size Estimation of Categorical Articulated Parts from a Single RGB-D Image (CVPR 2025 · similarity 0.87)
- SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference (NeurIPS 2025 · similarity 0.86)
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.86)
- MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images (CVPR 2024 · similarity 0.86)
- UA-Pose: Uncertainty-Aware 6D Object Pose Estimation and Online Object Completion with Partial References (CVPR 2025 · 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.