Research map / 3D vision / Human pose estimation
LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images
Grégory Rogez, Philippe Weinzaepfel, Cordelia Schmid
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 |
|---|---|---|---|
| add synthetic images rendered with Human3.6M poses (ablation) | LCR-Net · Human3.6M P2 (13 joints) | 3D pose error (mm), NMS: 89.8 -> 73.3 | Improved |
| add synthetic images rendered with CMU MoCap poses (ablation) | LCR-Net · Human3.6M P2 (13 joints) | 3D pose error (mm), NMS: 73.3 -> 68.5 | Improved |
| add RoI alignment (ablation) | LCR-Net · Human3.6M P2 (13 joints) | 3D pose error (mm), NMS: 68.5 -> 68.3 | No clear effect |
| add iterative estimation (ablation) | LCR-Net · Human3.6M P2 (13 joints) | 3D pose error (mm), NMS: 68.3 -> 67.7 | No clear effect |
| add rescoring of pose proposals (ablation) | LCR-Net · Human3.6M P2 (13 joints) | 3D pose error (mm), PPI Abs.: 68.7 -> 65.8 | Improved |
| replace VGG16 backbone with ResNet50 (ablation) | LCR-Net+ · Human3.6M P2 (13 joints) | 3D pose error (mm), PPI Align.: 56.4 -> 54.4 | No clear effect |
| add MS-Coco training set (ablation) | LCR-Net · MPII val (single-person) | PCKh@0.5 (%), PPI: 75.21 -> 79.95 | Improved |
| add synthetic CMU multi-person training data (ablation) | LCR-Net + MS-Coco · MPII val (single-person) | PCKh@0.5 (%), PPI: 79.95 -> 80.79 (+0.84%) | Improved |
| add RoI alignment (ablation) | LCR-Net · MPII val (single-person) | PCKh@0.5 (%), NMS: 76.30 -> 78.36 | Improved |
| add rescoring of pose proposals (ablation) | LCR-Net · MPII val (single-person) | PCKh@0.5 (%): NMS +1.54%, PPI +0.38% | Improved |
| replace VGG16 with ResNet50 backbone (ablation) | LCR-Net+ · MPII val (single-person) | PCKh@0.5 (%), PPI: 82.16 -> 86.87 | Improved |
| add 3D pose regression to 2D regression (ablation) | LCR-Net · MPII val (single-person) | PCKh@0.5 (%), NMS: 74.61 -> 76.30 | Improved |
Later papers that compared with this method
3 later accepted papers report LCR-Net++ as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.
- PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling (TPAMI 2022 · better on 1 of 1 shared result)
- PandaNet: Anchor-Based Single-Shot Multi-Person 3D Pose Estimation (CVPR 2020 · better on 2 of 2 shared results)
- HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimation (ECCV 2020 · better on 2 of 2 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- LCR-Net: Localization-Classification-Regression for Human Pose (CVPR 2017 · similarity 0.97)
- Towards Accurate Multi-Person Pose Estimation in the Wild (CVPR 2017 · similarity 0.90)
- 3D Human Pose Estimation From a Single Image via Distance Matrix Regression (CVPR 2017 · similarity 0.89)
- A Simple yet Effective Baseline for 3D Human Pose Estimation (ICCV 2017 · similarity 0.89)
- Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields (CVPR 2017 · similarity 0.89)
- DeeperCut: A Deeper, Stronger, and Faster Multi-person Pose Estimation Model (ECCV 2016 · similarity 0.89)
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.
