Research map / 3D vision / 3D generation
Hand Keypoint Detection in Single Images Using Multiview Bootstrapping
Check 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 Mix 3 RGB detection instead of the cited depth-based method | Tzionas single-hand and hand-object sequences · Tzionas dataset | average 2D error (pixels): 4.37 -> 5.49; 5.11 -> 5.67; 4.44 -> 4.15; 4.50 -> 4.81; 6.10 -> 5.75; 7.15 -> 9.79; 6.09 -> 5.47; 5.65 -> 4.35; 8.03 -> | Mixed |
| Use Mix 3 RGB detection instead of the cited method | Tzionas hand-hand interaction sequences · Tzionas dataset | average 2D error (pixels): 5.99 -> 9.10; 4.53 -> 6.95; 4.76 -> 10.09; 3.65 -> 5.31; 6.49 -> 6.55; 4.87 -> 6.09; 5.22 -> 10.35 | Hurt |
Closest papers by meaning
- Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation (AAAI 2024 · similarity 0.87)
- WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild (CVPR 2025 · similarity 0.85)
- ComPose: When to Trust Hands for Object Pose Tracking (NeurIPS 2026 · similarity 0.84)
- EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild (CVPR 2025 · similarity 0.84)
- Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera (CVPR 2025 · similarity 0.84)
- HandOS: 3D Hand Reconstruction in One Stage (CVPR 2025 · similarity 0.84)
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.