Research map / 3D vision / Human pose estimation
ELLIPSDF: Joint Object Pose and Shape Optimization With a Bi-Level Ellipsoid and Signed Distance Function Description
Mo Shan, Qiaojun Feng, You-Yi Jau, Nikolay Atanasov
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 SDF-residual optimization after initialization (ablation) | ELLIPSDF · ScanNet object pose | Pose accuracy (%): 31.5 -> 39.6 | Improved |
| add coarse-level ellipsoid residual to fine-level SDF (ablation) | ELLIPSDF (fine) · ScanNet shape | Average fitting rate (%): 85.9 -> 89.0 | Improved |
| add coarse-level ellipsoid residual (ablation) | ELLIPSDF (fine) · ScanNet shape, display | Fitting rate (%): 90.6 -> 96.9 | Improved |
| add coarse-level ellipsoid residual (ablation) | ELLIPSDF (fine) · ScanNet shape, table | Fitting rate (%): 76.2 -> 77.3 | Improved |
| add coarse-level ellipsoid residual (ablation) | ELLIPSDF (fine) · ScanNet 3D detection, display | mAP@IoU=0.5: 0.25 -> 0.31 | Improved |
| add coarse-level ellipsoid residual (ablation) | ELLIPSDF (fine) · ScanNet 3D detection, chair | mAP@IoU=0.5: 0.42 -> 0.43 | Improved |
| use ELLIPSDF instead of MOLTR | MOLTR · ScanNet 3D detection, table | mAP@IoU=0.5: 0.06 -> 0.27 | Improved |
| use ELLIPSDF (opt) instead of Vid2CAD | Vid2CAD · ScanNet object pose | Pose accuracy (%): 38.3 -> 39.6 | Improved |
Closest papers by meaning
- Perspective-1-Ellipsoid: Formulation, Analysis and Solutions of the Camera Pose Estimation Problem from One Ellipse-Ellipsoid Correspondence (IJCV 2023 · similarity 0.88)
- Object-Based Visual Camera Pose Estimation From Ellipsoidal Model and 3D-Aware Ellipse Prediction (IJCV 2022 · similarity 0.88)
- In-Hand 3D Object Scanning From an RGB Sequence (CVPR 2023 · similarity 0.87)
- ComPose: A Unified Completion-Pose Framework for Robust Category-Level Object Pose Estimation (CVPR 2026 · similarity 0.85)
- UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image (CVPR 2025 · similarity 0.85)
- SchemaPose: RGB-Based Category-Level Pose Estimation with Parametric Category Schema (NeurIPS 2026 · similarity 0.84)
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.
