Research map / 3D vision / Human pose estimation
Real-Time Joint Tracking of a Hand Manipulating an Object from RGB-D Input
Srinath Sridhar, Franziska Mueller, Michael Zollhöfer, Dan Casas, Antti Oulasvirta, Christian Theobalt
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 |
|---|---|---|---|
| use continuous articulated 3D Gaussian mixture alignment instead of 2.5D formulation (ablation) | hand tracking · Dexter dataset | average fingertip error (mm): 19.6 -> 17.2 | Improved |
| add viewpoint selection to the energy (ablation) | hand-object tracker · Hand-object benchmark | average error | Improved |
| add semantic alignment, occlusion handling and contact points terms to data term (ablation) | hand-object tracker · Hand-object benchmark | average error | Improved |
| use the data term alone (ablation) | hand-object tracker · Hand-object benchmark | average error | Hurt |
| compare to slower prior hand-object method | hand-object tracker · IJCV dataset | fingertip pixel error (px): 8.6px, about 2px higher, over 60 times faster | Mixed |
| add occlusion-aware hand-object terms versus prior hand tracker | hand-object tracker · occlusion sequences | tracking under finger occlusion | Improved |
Closest papers by meaning
- Real-Time Hand Tracking Under Occlusion From an Egocentric RGB-D Sensor (ICCV 2017 · similarity 0.91)
- ComPose: When to Trust Hands for Object Pose Tracking (NeurIPS 2026 · similarity 0.90)
- Capturing Hands in Action Using Discriminative Salient Points and Physics Simulation (IJCV 2016 · similarity 0.90)
- Joint 3D tracking of a deformable object in interaction with a hand (ECCV 2018 · similarity 0.90)
- HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos (CVPR 2025 · similarity 0.87)
- HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 · 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.
