Research map / 3D vision / Human pose estimation
Aligning Latent Spaces for 3D Hand Pose Estimation
Linlin Yang, Shile Li, Dongheui Lee, 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 |
|---|---|---|---|
| add heatmap decoder to the RGB-pose baseline (ablation) | S1 baseline · RHD | mean EPE (mm): 16.61 -> 16.10 | Improved |
| add point cloud decoder to the RGB-pose baseline (ablation) | S1 baseline · RHD | mean EPE (mm): 16.61 -> 15.91 | Improved |
| add both heatmap and point cloud decoders (ablation) | S1 baseline · RHD | mean EPE (mm): 16.61 -> 15.49 | Improved |
| add point cloud encoder aligned with KL divergence (ablation) | S2 (R2CHP) · RHD | mean EPE (mm): 15.49 -> 14.93 | Improved |
| replace KL alignment with product of Gaussian experts (ablation) | S3 · RHD | mean EPE (mm): 14.93 -> 13.14 | Improved |
| add viewpoint correction to the baseline R2P (ablation) | R2P · RHD | AUC: 0.869 -> 0.898 | Improved |
| replace KL alignment with product of Gaussian experts (ablation) | RC2CHP · RHD | AUC: 0.931 -> 0.943 | Improved |
| use proposed method over best VAE-based baseline | Ours vs Spurr et al. · RHD | mean EPE (mm): 19.73 -> 13.14 | Improved |
| use proposed method over best VAE-based baseline | Ours vs Spurr et al. · STB | mean EPE (mm): 8.56 -> 7.05 | Improved |
| use proposed method over Iqbal et al. | Ours · RHD | mean EPE (mm): 13.41 -> 13.14 | Improved |
| use proposed method over Iqbal et al. on STB AUC | Ours · STB 3D PCK | AUC: 0.994 -> 0.996 | Improved |
| add unlabelled point-cloud data in weakly-supervised training (ablation) | RC2CHP · RHD (5% to 100% labelled) | mean EPE (mm): up to 6% | Improved |
Closest papers by meaning
- 3D Hand Pose Estimation Using Synthetic Data and Weakly Labeled RGB Images (TPAMI 2020 · similarity 0.93)
- Weakly-supervised 3D Hand Pose Estimation from Monocular RGB Images (ECCV 2018 · similarity 0.93)
- 3D Hand Shape and Pose Estimation From a Single RGB Image (CVPR 2019 · similarity 0.91)
- 3D Hand Pose Estimation via Articulated Anchor-to-Joint 3D Local Regressors (TPAMI 2025 · similarity 0.91)
- Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation (AAAI 2024 · similarity 0.91)
- Cross-Modal Deep Variational Hand Pose Estimation (CVPR 2018 · similarity 0.91)
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.
