Research map / 3D vision / Human pose estimation
3D Interacting Hand Pose Estimation by Hand De-Occlusion and Removal
Hao Meng, Sheng Jin, Wentao Liu, Chen Qian, Mengxiang Lin, Wanli Ouyang, Ping Luo
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 distractor removal (ablation) | HDR · InterHand2.6M M branch, IH26M-ALL | MPJPE (mm): 24.16 -> 17.98 | Improved |
| add de-occlusion (ablation) | HDR · InterHand2.6M M branch, IH26M-ALL | MPJPE (mm): 19.69 -> 17.98 | Improved |
| add HDR to single-hand estimator (ablation) | SHPE · InterHand2.6M M branch, IH26M-ALL | MPJPE (mm): 25.78 -> 17.98 | Improved |
| add discriminator (ablation) | HDRNet · InterHand2.6M M branch, IH26M-ALL | MPJPE (mm): 18.11 -> 17.98 | No clear effect |
| add transformer blocks (ablation) | HDRNet · InterHand2.6M M branch, IH26M-ALL | MPJPE (mm): 18.85 -> 17.98 | Improved |
| combine AIH_Syn with AIH_Render (ablation) | HDRNet training · InterHand2.6M M branch, IH26M-ALL | MPJPE (mm): 18.10 -> 17.98 | Improved |
| combine AIH_Render with AIH_Syn (ablation) | HDRNet training · InterHand2.6M M branch, IH26M-ALL | MPJPE (mm): 18.35 -> 17.98 | Improved |
| add HDR (ablation) | SHPE · InterHand2.6M M branch, IH26M-IH | MPJPE (mm): 40.98 -> 25.45 | Improved |
| add HDR | SHPE · InterHand2.6M ALL branch, IH26M-IH | MPJPE (mm): 39.96 -> 25.93 | Improved |
| add AIH data to SHPE training (ablation) | SHPE · InterHand2.6M M branch, IH26M-IH | MPJPE (mm): 40.98 -> 32.27 | Improved |
| add AIH data to SHPE+HDR training (ablation) | SHPE+HDR · InterHand2.6M M branch, IH26M-IH | MPJPE (mm): 25.45 -> 24.59 | Improved |
| add HDR | SHPE · Tzionas dataset | 2D EPE: 14.88 -> 8.70 | Improved |
Closest papers by meaning
- InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image (ECCV 2020 · similarity 0.91)
- RenderIH: A Large-Scale Synthetic Dataset for 3D Interacting Hand Pose Estimation (ICCV 2023 · similarity 0.90)
- FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape From Single RGB Images (ICCV 2019 · similarity 0.89)
- Deformer: Dynamic Fusion Transformer for Robust Hand Pose Estimation (ICCV 2023 · similarity 0.89)
- End-to-End Detection and Pose Estimation of Two Interacting Hands (ICCV 2021 · similarity 0.89)
- EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild (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.
