Research map / 3D vision / Human pose estimation
Panoptic Studio: A Massively Multiview System for Social Interaction Capture
Hanbyul Joo, Tomas Simon, Xulong Li, Hao Liu, Lei Tan, Lin Gui, Sean Banerjee, Timothy Godisart, Bart C. Nabbe, Iain Matthews, Takeo Kanade A, Shohei Nobuhara and 1 more
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 more camera views (up to 480 VGA) (ablation) | Stage 1 reconstruction · 160226 ultimatum1 PCK | PCK accuracy | Improved |
| increase resolution (HD or VGA vs QVGA) with the same 19 cameras (ablation) | Stage 1 reconstruction · 160226 ultimatum1 PCK | PCK accuracy: HD about 7 times more pixels than VGAs and about 27 times more than QVGAs | No clear effect |
| add Stage 2 trajectory-stream refinement (ablation) | Panoptic Studio method · 160226 mafia2 right wrist X coordinate | jitter and missing frames | Improved |
| use presented method instead of Joo et al. | Panoptic Studio method · 150129 007Bang | accuracy (%): 80.80% -> 99.99% | Improved |
| use many cameras instead of Oracle fusion of multiple Kinects | Panoptic Studio method · 160226 ultimatum1 PCK at 5 cm | PCK accuracy: Kinects less than 80% at 5cm | Improved |
| benefit of more views grows with number of people in scene (ablation) | Stage 1 reconstruction · 160226 ultimatum1 | PCK accuracy | Improved |
Closest papers by meaning
- HOI-M^3: Capture Multiple Humans and Objects Interaction within Contextual Environment (CVPR 2024 · similarity 0.87)
- Generative Proxemics: A Prior for 3D Social Interaction from Images (CVPR 2024 · similarity 0.87)
- Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning (CVPR 2025 · similarity 0.87)
- Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture (CVPR 2025 · similarity 0.86)
- Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions (NeurIPS 2024 · similarity 0.86)
- Capturing Closely Interacted Two-Person Motions with Reaction Priors (CVPR 2024 · similarity 0.86)
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.
