Research map / 3D vision / Human pose estimation
FreiHAND: A Dataset for Markerless Capture of Hand Pose and Shape From Single RGB Images
Christian Zimmermann, Duygu Ceylan, Jimei Yang, Bryan Russell, Max Argus, Thomas Brox
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 background compositing (Cut&Paste) to green screen images (ablation) | FreiHAND training · FreiHAND eval (from scratch) | 3D PCK AUC: 0.440 -> 0.508 | Improved |
| add harmonization to Cut&Paste (ablation) | FreiHAND training · FreiHAND eval (from scratch) | 3D PCK AUC: 0.508 -> 0.628 | Improved |
| combine all post-processing options jointly (ablation) | FreiHAND training · FreiHAND eval (from scratch) | 3D PCK AUC: 0.643 -> 0.678 | Improved |
| add compositing post-processing with a pretrained ResNet50 (ablation) | FreiHAND training · FreiHAND eval (ResNet50 pretrained) | 3D PCK AUC: 0.436 -> 0.523 | Improved |
| add compositing post-processing when training on RHD (ablation) | RHD training · FreiHAND eval | 3D PCK AUC: 0.508 -> 0.514 | No clear effect |
| add post-processing to RHD training, evaluated on RHD (ablation) | RHD training · RHD eval | 3D PCK AUC: 0.767 -> 0.756 | Hurt |
| grow the labeled dataset from D0 to D4 through iterative labeling (ablation) | FreiHAND · RHD eval | 3D PCK AUC: 0.244 -> 0.518 | Improved |
| grow the labeled dataset from D0 to D4 through iterative labeling (ablation) | FreiHAND · PAN eval | 3D PCK AUC: 0.347 -> 0.562 | Improved |
| predict MANO parameters with a CNN instead of fitting MANO to predicted keypoints (ablation) | shape estimation · FreiHAND eval | mesh error: 1.44 -> 1.07 | Improved |
| predict MANO parameters with a CNN instead of fitting MANO to predicted keypoints (ablation) | shape estimation · FreiHAND eval | F@5mm: 0.416 -> 0.529 | Improved |
| use ImageNet-pretrained ResNet50 instead of from-scratch network, trained on FreiHAND | FreiHAND training · FreiHAND eval | 3D PCK AUC: 0.678 -> 0.523 | Hurt |
| use Scorevolume loss instead of Softargmax loss for MVNet (ablation) | MVNet · labeling confidence | sparsification curve | Mixed |
Closest papers by meaning
- 3D Hand Shape and Pose Estimation From a Single RGB Image (CVPR 2019 · similarity 0.92)
- InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image (ECCV 2020 · similarity 0.92)
- SeqHAND: RGB-Sequence-Based 3D Hand Pose and Shape Estimation (ECCV 2020 · similarity 0.91)
- ArtiBoost: Boosting Articulated 3D Hand-Object Pose Estimation via Online Exploration and Synthesis (CVPR 2022 · similarity 0.91)
- HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 · similarity 0.89)
- SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit Meshes (NeurIPS 2025 · similarity 0.89)
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.
