Research map / 3D vision / Human pose estimation
Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields
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 3-scale search instead of one scale (ablation) | Pose estimator · MPII full testing set | mAP: 72.5 -> 75.6 | Helped |
| Train the association network on PAFs rather than midpoint representations (ablation) | Pose estimator · MPII validation set, PCKh-0.5 | mAP: +2.9% vs one-midpoint; +2.3% vs two intermediate points | Helped |
| Mask unlabeled people in the training loss (ablation) | PAF pose estimator · MPII validation set, PCKh-0.5 | mAP: +2.3% | Helped |
| Use ground-truth keypoint locations with the parsing algorithm (ablation) | PAF parsing · MPII validation set | mAP: 88.3% | Helped |
| Use ground-truth connections with predicted keypoints (ablation) | PAF pose estimator · MPII validation set | mAP: 81.6% | Helped |
| Use a separately trained model with minimal tree association edges (ablation) | Pose estimator · MPII validation set | mAP: 77.4 -> 79.1 | Helped |
| Apply CPM refinement to parsed person regions (ablation) | Pose estimator · COCO validation set | AP: 58.4 -> 61.0 | Helped |
| Use a person detector plus CPM instead of bottom-up pose estimation | COCO validation set pose estimation · COCO validation set | AP: 62.7 vs 58.4; 52.7 | Mixed |
Closest papers by meaning
- Efficient Online Multi-Person 2D Pose Tracking With Recurrent Spatio-Temporal Affinity Fields (CVPR 2019 · similarity 0.91)
- PifPaf: Composite Fields for Human Pose Estimation (CVPR 2019 · similarity 0.89)
- Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation (AAAI 2020 · similarity 0.89)
- DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation (CVPR 2016 · similarity 0.89)
- Detangling People: Individuating Multiple Close People and Their Body Parts via Region Assembly (CVPR 2017 · similarity 0.89)
- AdaptivePose: Human Parts as Adaptive Points (AAAI 2022 · similarity 0.88)
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.