Research map / Detection and segmentation / Open-set and few-shot detection
Multi-Path Learning for Object Pose Estimation Across Domains
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 one multi-path encoder instead of 30 separately trained AAEs | T-LESS pose estimation with ground-truth masks · T-LESS total | VSD recall: 41.52 -> 43.24 | Helped |
| Use one multi-path encoder instead of 30 separately trained AAEs | T-LESS pose estimation with ground-truth bounding boxes · T-LESS objects 19-30 | VSD recall: 42.45 -> 33.17 | Hurt |
| Use ground-truth masks rather than ground-truth bounding boxes | MP-Encoder trained on T-LESS objects 1-18 · T-LESS objects 19-30 | VSD recall: 33.17 -> 43.33 | Helped |
| Use the MP-Encoder iterative render-inference refinement instead of DeepIM refinement | ModelNet40 novel instances in seen categories · ModelNet40 | recall at (5° , 5cm): 79.3 -> 96.6 | Helped |
| Use the MP-Encoder iterative render-inference refinement instead of DeepIM refinement | ModelNet40 novel categories · ModelNet40 | recall at (5° , 5cm): 64.3 -> 84.8 | Helped |
| Use the MP-Encoder iterative render-inference refinement instead of DeepIM refinement | ModelNet40 novel categories · ModelNet40 | Proj2D (5px): 73.3 -> 81.6 | Mixed |
| Replace the shallow CNN with a ResNet101 backbone and spatial pyramid pooling (ablation) | MP-Encoder · T-LESS and ModelNet40 pose encoding | downstream pose performance | No clear effect |
| Train without random background images (ablation) | MP-Encoder synthetic-to-real generalization · Real object views | generalization | Hurt |
Closest papers by meaning
- One2Any: One-Reference 6D Pose Estimation for Any Object (CVPR 2025 · similarity 0.88)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.88)
- NOPE: Novel Object Pose Estimation from a Single Image (CVPR 2024 · similarity 0.88)
- Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval (CVPR 2024 · similarity 0.87)
- Co-op: Correspondence-based Novel Object Pose Estimation (CVPR 2025 · similarity 0.87)
- Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation (ICLR 2024 · 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.