Research map / 3D vision / Human pose estimation
Cross-Modal Deep Variational Hand Pose Estimation
Read the paperCheck 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 the cross-modal hand-pose model with handedness, scale, and translation invariances | RHD 2D→3D · RHD | mean EPE (mm): 22.43 -> 17.14 | Helped |
| Use the cross-modal hand-pose model with handedness, scale, and translation invariances | RHD RGB→3D · RHD | mean EPE (mm): 30.42 -> 19.73 | Helped |
| Use the cross-modal hand-pose model with handedness, scale, and translation invariances | STB RGB→3D · STB | mean EPE (mm): 8.68 -> 8.56 | Helped |
| Add 3D→3D reconstruction (ablation) | Var. 1 cross-modal VAE · RHD 2D→3D | mean EPE (mm): 17.23 -> 17.82 | Hurt |
| Add 2D→2D reconstruction (ablation) | Var. 1 cross-modal VAE · RHD 2D→3D | mean EPE (mm): 17.23 -> 17.14 | Helped |
| Add 2D→2D reconstruction (ablation) | Var. 1 cross-modal VAE · RHD RGB→3D | mean EPE (mm): 19.73 -> 20.04 | Hurt |
| Add 2D→2D reconstruction (ablation) | Var. 1 cross-modal VAE · STB RGB→3D | mean EPE (mm): 8.75 -> 8.56 | Helped |
| Add RGB→RGB and 3D→3D reconstruction (ablation) | Var. 1 cross-modal VAE · STB RGB→3D | mean EPE (mm): 8.75 -> 9.57 | Hurt |
| Add 3D→3D reconstruction (ablation) | Var. 1 cross-modal VAE · STB RGB→3D | mean EPE (mm): 8.75 -> 8.61 | Helped |
| Remove handedness invariance (ablation) | Ours (T+S+H) · RHD 2D→3D | mean EPE (mm): 17.14 -> 18.90 | Hurt |
| Remove scale invariance (ablation) | Ours (T+S+H) · RHD RGB→3D | mean EPE (mm): 19.73 -> 22.34 | Hurt |
| Remove handedness and scale invariances (ablation) | Ours (T+S+H) · STB RGB→3D | mean EPE (mm): 8.56 -> 9.49 | Hurt |
Closest papers by meaning
- Cross-Domain 3D Hand Pose Estimation With Dual Modalities (CVPR 2023 · similarity 0.93)
- Crossing Nets: Combining GANs and VAEs With a Shared Latent Space for Hand Pose Estimation (CVPR 2017 · similarity 0.91)
- Disentangling Latent Hands for Image Synthesis and Pose Estimation (CVPR 2019 · similarity 0.91)
- Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation (AAAI 2024 · similarity 0.90)
- Reconstructing Hands in 3D with Transformers (CVPR 2024 · similarity 0.87)
- The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction (NeurIPS 2026 · 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.