Research map / 3D vision / Human pose estimation
Mask as Supervision: Leveraging Unified Mask Information for Unsupervised 3D Pose Estimation
Yuchen Yang, Yu Qiao, Xiao Sun
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 geodesic weighting to the mask loss (ablation) | Mask as Supervision · Human3.6M | MPJPE (mm): 102.6 -> 95.9 | Improved |
| add Shape Prior Network (physique mask) and geodesic weighting (ablation) | Mask as Supervision with triangulation · Human3.6M | MPJPE (mm): 127.4 -> 95.9 | Improved |
| add multi-view triangulation to resolve left-right reversal (ablation) | Mask as Supervision · Human3.6M | Ambiguity Ratio: 48.73% -> 23.34% | Improved |
| add multi-view triangulation (MPJPE side) (ablation) | Mask as Supervision · Human3.6M | MPJPE (mm): 118.1 -> 127.4 | Hurt |
| add supervised post-processing to the baseline (ablation) | Baseline Gaussian mask · Human3.6M | skeleton plausibility | Improved |
| scale up unlabeled in-the-wild training data (add TikTok) | Mask as Supervision · MPII (in the wild) | pose accuracy | Improved |
| replace Batch Normalization with Group Normalization | detector · Human3.6M | left-right ambiguity | Improved |
| apply SPP post-processing on MPI-INF-3DHP | Mask as Supervision · MPI-INF-3DHP | PCK: 60.2 -> 71.3 | Improved |
| use unsupervised mask supervision on MPI-INF-3DHP against Honari et al. | Mask as Supervision · MPI-INF-3DHP | MPJPE (cm): 19.36 vs 14.57 | Mixed |
Closest papers by meaning
- Kinematic-Structure-Preserved Representation for Unsupervised 3D Human Pose Estimation (AAAI 2020 · similarity 0.89)
- Unsupervised 3D Pose Estimation With Geometric Self-Supervision (CVPR 2019 · similarity 0.88)
- ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses (CVPR 2022 · similarity 0.88)
- Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos (CVPR 2024 · similarity 0.88)
- Optimizing Human Pose Estimation Through Focused Human and Joint Regions (AAAI 2025 · similarity 0.87)
- A Unified Masked Autoencoder with Patchified Skeletons for Motion Synthesis (AAAI 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.
