Research map / 3D vision / Human pose estimation
Novel Object Viewpoint Estimation Through Reconstruction Alignment
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 |
|---|---|---|---|
| Use reconstruction-alignment instead of direct pose prediction | relative viewpoint estimation · ShapeNet → Thingi10K | Accπ/6: 25.00 -> 40.12 | Helped |
| Use reconstruction-alignment instead of direct pose prediction | relative viewpoint estimation · Pix3D → Thingi10K | Accπ/6: 14.43 -> 33.00 | Helped |
| Use reconstruction-alignment instead of direct pose prediction | relative viewpoint estimation · Thingi10K → Thingi10K | Accπ/6: 20.82 -> 41.25 | Helped |
| Use reconstruction-alignment instead of direct pose prediction | relative viewpoint estimation · ShapeNet → ShapeNet | Accπ/6: 60.23 -> 47.57 | Hurt |
| Use reconstruction-alignment instead of direct pose prediction | relative viewpoint estimation · Pix3D → Pix3D | Accπ/6: 68.93 -> 58.08 | Hurt |
| Add space carving to the 3D feature representation (ablation) | Ours · ShapeNet → ShapeNet | Accπ/6: 6.38 -> 47.57 | Helped |
| Add space carving to the 3D feature representation (ablation) | Ours · ShapeNet → Thingi10K | Accπ/6: 4.21 -> 40.12 | Helped |
| Add space carving to the 3D feature representation (ablation) | Ours · ShapeNet → ShapeNet | IoU: 0.64 -> 0.83 | Helped |
| Add space carving to the 3D feature representation (ablation) | Ours · ShapeNet → Thingi10K | IoU: 0.63 -> 0.82 | Helped |
| Add 3D refinement to the feature representation (ablation) | Ours · ShapeNet → ShapeNet | IoU: 0.63 -> 0.83 | Helped |
| Add 3D refinement to the feature representation (ablation) | Ours · ShapeNet → Thingi10K | IoU: 0.64 -> 0.82 | Helped |
| Add 3D refinement to the feature representation (ablation) | Ours · ShapeNet → ShapeNet | Accπ/6: 47.57 -> 47.57 | No clear effect |
Closest papers by meaning
- NOPE: Novel Object Pose Estimation from a Single Image (CVPR 2024 · similarity 0.90)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.89)
- 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation (ICLR 2024 · similarity 0.89)
- UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image (CVPR 2025 · similarity 0.88)
- Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis (NeurIPS 2024 · similarity 0.88)
- RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects (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.