Research map / 3D vision / Human pose estimation
DeepCap: Monocular Human Performance Capture Using Weak Supervision
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 |
|---|---|---|---|
| add multi-view training supervision instead of training with a single camera view (ablation) | DeepCap · S4 sequence | 3DPCK (%): 62.11 -> 93.52 | Helped |
| add multi-view training supervision instead of training with a single camera view (ablation) | DeepCap · S4 sequence | AMVIoU (%): 65.11 -> 78.44 | Helped |
| increase training views from 2 to 7 (ablation) | DeepCap · S4 sequence | 3DPCK (%): 93.52 -> 95.95 | Helped |
| increase training views from 2 to 7 (ablation) | DeepCap · S4 sequence | AMVIoU (%): 78.44 -> 81.73 | Helped |
| increase training images from 6500 to 13000 (ablation) | DeepCap · S4 sequence | 3DPCK (%): 85.19 -> 92.25 | Helped |
| increase training images from 6500 to 13000 (ablation) | DeepCap · S4 sequence | AMVIoU (%): 73.41 -> 78.97 | Helped |
| add DefNet non-rigid deformation to PoseNet-only template animation (ablation) | DeepCap · S4 sequence | AMVIoU (%): 78.51 -> 82.53 | Helped |
| fine-tune the networks on in-the-wild test images using single-view keypoint and silhouette losses | DeepCap · in-the-wild images | reconstruction performance | Helped |
Closest papers by meaning
- Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation From Monocular Video (CVPR 2022 · similarity 0.86)
- Monocular Total Capture: Posing Face, Body, and Hands in the Wild (CVPR 2019 · similarity 0.86)
- EventCap: Monocular 3D Capture of High-Speed Human Motions Using an Event Camera (CVPR 2020 · similarity 0.85)
- Feed-forward Human Performance Capture via Progressive Canonical Space Updates (ICLR 2026 · similarity 0.85)
- Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture (CVPR 2025 · similarity 0.84)
- ODHSR: Online Dense 3D Reconstruction of Humans and Scenes from Monocular Videos (CVPR 2025 · similarity 0.83)
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.