Research map / 3D vision / Human pose estimation
Multiview-Consistent Semi-Supervised Learning for 3D Human Pose Estimation
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 multiview-consistent metric learning to pose-regression training | MCSS on Human3.6M with S1 supervision · Human3.6M Protocol 2, S1 supervision | N-MPJPE: 149.28 -> 111.94 | Helped |
| Regress canonical rather than global-coordinate pose (ablation) | MCSS on Human3.6M with S1 supervision · Human3.6M Protocol 2, S1 supervision | N-MPJPE: 157.30 -> 111.94 | Helped |
| Use ResNet-34 instead of the ResNet-18 backbone (ablation) | MCSS on Human3.6M with S1 supervision · Human3.6M Protocol 2, S1 supervision | N-MPJPE: 111.94 -> 115.85 | Hurt |
| Fine-tune the Human3.6M-trained embedding with multiview metric loss on MPI-INF-3DHP | MCSS cross-view pose retrieval · MPI-INF-3DHP | Mean-PA-MPJPE@10: 119.6 -> 62.46 | Helped |
| Use the smaller ResNet-18 feature extractor rather than ResNet-50 | MCSS inference · NVIDIA 1080Ti inference | inference time: 75.3ms -> 24.8ms | Helped |
Closest papers by meaning
- Weakly-Supervised 3D Human Pose Learning via Multi-View Images in the Wild (CVPR 2020 · similarity 0.92)
- 3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Training (CVPR 2019 · similarity 0.90)
- COMPOSE: Hypergraph Cover Optimization for Multi-view 3D Human Pose Estimation (NeurIPS 2026 · similarity 0.88)
- MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation (CVPR 2025 · similarity 0.87)
- PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation (CVPR 2025 · similarity 0.87)
- SVTformer: Spatial-View-Temporal Transformer for Multi-View 3D Human Pose Estimation (AAAI 2025 · 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.