Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision

We propose a CNN-based approach for 3D human body pose estimation from single RGB images that addresses the issue of limited generalizability of models trained solely on the starkly limited publicly available 3D pose data. Using only the existing 3D pose data and 2D pose data, we show state-of-the-art performance on established benchmarks through transfer of learned features, while also generalizing to in-the-wild scenes. We further introduce a new training set for human body pose estimation from monocular images of real humans that has the ground truth captured with a multi-camera marker-less motion capture system. It complements existing corpora with greater diversity in pose, human appearance, clothing, occlusion, and viewpoints, and enables an increased scope of augmentation. We also contribute a new benchmark that covers outdoor and indoor scenes, and demonstrate that our 3D pose dataset shows better in-the-wild performance than existing annotated data, which is further improved in conjunction with transfer learning from 2D pose data. All in all, we argue that the use of transfer learning of representations in tandem with algorithmic and data contributions is crucial for general 3D body pose estimation.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Human Pose Estimation Human3.6M 3DPoseNet Average MPJPE (mm) 72.88 # 282
3D Human Pose Estimation MPI-INF-3DHP Mehta AUC 40.8 # 63
PCK 64.7 # 82

Results from Other Papers


Task Dataset Model Metric Name Metric Value Rank Source Paper Compare
Pose Estimation Leeds Sports Poses Mehta PCK 75.7 # 17
3D Human Pose Estimation MPI-INF-3DHP Mehta AUC 39.3 # 67
MPJPE 117.6 # 80
PCK 75.7 # 73

Methods


No methods listed for this paper. Add relevant methods here