Research map / Detection and segmentation / Weakly supervised detection and segmentation
DSC-PoseNet: Learning 6DoF Object Pose Estimation via Dual-Scale Consistency
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 normalized object scale instead of only random crops (ablation) | DSC-PoseNet · LINEMOD | ADD | Helped |
| Use normalized scale 64 rather than normalized scale 128 (ablation) | DSC-PoseNet · LINEMOD | ADD: 54.7% versus 54.0% | Mixed |
| Add annotated poses to training (ablation) | DSC-PoseNet · LINEMOD | ADD: 54.7% versus 85.9% | Helped |
| Use keypoint offsets with attention instead of direct soft-argmax keypoint estimation (ablation) | DSC-PoseNet · occluded keypoints | training stability | Helped |
Closest papers by meaning
- MRC-Net: 6-DoF Pose Estimation with MultiScale Residual Correlation (CVPR 2024 · similarity 0.90)
- SMOC-Net: Leveraging Camera Pose for Self-Supervised Monocular Object Pose Estimation (CVPR 2023 · similarity 0.90)
- Segmentation-Driven 6D Object Pose Estimation (CVPR 2019 · similarity 0.89)
- Coarse-To-Fine Volumetric Prediction for Single-Image 3D Human Pose (CVPR 2017 · similarity 0.89)
- NOPE: Novel Object Pose Estimation from a Single Image (CVPR 2024 · similarity 0.88)
- Co-op: Correspondence-based Novel Object Pose Estimation (CVPR 2025 · similarity 0.88)
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.