Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision
This addresses the problem of accurate 3D pose estimation in real-world scenes for computer vision applications, with incremental improvements through data and transfer learning.
The paper tackles the limited generalizability of monocular 3D human pose estimation by proposing a CNN-based approach that uses transfer learning from 2D pose data and introduces a new diverse training set, achieving state-of-the-art performance on benchmarks and better in-the-wild results.
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.