Research map / Label-efficient and robust learning / Domain adaptation and generalization
Synthetic-to-Real Pose Estimation with Geometric Reconstruction
Qiuxia Lin, Kerui Gu, Linlin Yang, Angela Yao
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 |
|---|---|---|---|
| replace UniFrame pseudo-labelling with integrated 2D+3D-kinematic selection (ablation) | Ours · RHD->H3D | PCK@0.05: 80.2 -> 81.4 | Improved |
| replace UniFrame pseudo-labelling with integrated selection (ablation) | Ours · SURREAL->Human3.6M | PCK@0.05: 79.8 -> 80.8 | Improved |
| add geometric reconstruction loss L_rec (ablation) | Ours · RHD->H3D | PCK@0.05: 81.6 -> 84.1 | Improved |
| add geometric reconstruction loss L_rec (ablation) | Ours · SURREAL->Human3.6M | PCK@0.05: 81.2 -> 83.7 | Improved |
| use warping estimation (bone maps) instead of heatmap-only reconstruction (ablation) | Ours · RHD->H3D | PCK@0.05: 81.6 -> 84.1 | Improved |
| heatmap-only reconstruction on top of pseudo-labelling (ablation) | Ours · RHD->H3D | PCK@0.05: 81.4 -> 81.6 | No clear effect |
| add temporal consistency loss on consecutive frames for fair comparison (ablation) | RegDA · RHD->MVHand | PCK@0.05: +0.6 | Improved |
| add temporal consistency loss on consecutive frames (ablation) | UniFrame · SURREAL->Human3.6M | PCK@0.05: +0.3 | Improved |
| frame stride [5, 15] versus [0, 5] (ablation) | Ours · SURREAL->Human3.6M | PCK@0.05: 81.8 -> 83.7 | Improved |
| frame stride [30, 50] versus [5, 15] (ablation) | Ours · SURREAL->Human3.6M | PCK@0.05: 83.7 -> 82.5 | Hurt |
| integrated pseudo-labelling selection vs UniFrame selection (ablation) | Ours · MVHand pseudo-label accuracy | percentage of correct pseudo-labels: 59% -> 72% | Improved |
| add reconstruction loss for confident-but-inaccurate keypoints (ablation) | Ours · Human3.6M train keypoints | pseudo-label PCK | Improved |
Closest papers by meaning
- Prior-guided Source-free Domain Adaptation for Human Pose Estimation (ICCV 2023 · similarity 0.89)
- From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation (CVPR 2021 · similarity 0.89)
- Analyzing the Synthetic-to-Real Domain Gap in 3D Hand Pose Estimation (CVPR 2025 · similarity 0.87)
- Fast Adaptation for Human Pose Estimation via Meta-Optimization (CVPR 2024 · similarity 0.86)
- Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation (ICLR 2024 · similarity 0.86)
- FlexPose: Pose Distribution Adaptation with Limited Guidance (AAAI 2025 · similarity 0.85)
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.
