Probabilistic Monocular 3D Human Pose Estimation with Normalizing Flows

• Published in: 2021 IEEE/CVF International Conference on Computer Vision (ICCV) pp. 11179 - 11188
• Main Authors: Wehrbein, Tom, Rudolph, Marco, Rosenhahn, Bodo, Wandt, Bastian
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-10-2021
• Subjects: Computer vision; Gestures and body pose; 3D from a single image and shape-from-x; Detection and localization in 2D and 3D; Motion and tracking; Vision applications and systems; Heating systems; Inverse problems; Measurement; Three-dimensional displays; Training; Uncertainty
• DOI: 10.1109/ICCV48922.2021.01101
• EISSN: 2380-7504

3D human pose estimation from monocular images is a highly ill-posed problem due to depth ambiguities and occlusions. Nonetheless, most existing works ignore these ambiguities and only estimate a single solution. In contrast, we generate a diverse set of hypotheses that represents the full posterior distribution of feasible 3D poses. To this end, we propose a normalizing flow based method that exploits the deterministic 3D-to-2D mapping to solve the ambiguous inverse 2D-to-3D problem. Additionally, uncertain detections and occlusions are effectively modeled by incorporating uncertainty information of the 2D detector as condition. Further keys to success are a learned 3D pose prior and a generalization of the best-of-M loss. We evaluate our approach on the two benchmark datasets Human3.6M and MPI-INF-3DHP, outperforming all comparable methods in most metrics. The implementation is available on GitHub 1 .