6D Rotation Representation For Unconstrained Head Pose Estimation

25 Feb 2022  ·  Thorsten Hempel, Ahmed A. Abdelrahman, Ayoub Al-Hamadi ·

In this paper, we present a method for unconstrained end-to-end head pose estimation. We address the problem of ambiguous rotation labels by introducing the rotation matrix formalism for our ground truth data and propose a continuous 6D rotation matrix representation for efficient and robust direct regression. This way, our method can learn the full rotation appearance which is contrary to previous approaches that restrict the pose prediction to a narrow-angle for satisfactory results. In addition, we propose a geodesic distance-based loss to penalize our network with respect to the SO(3) manifold geometry. Experiments on the public AFLW2000 and BIWI datasets demonstrate that our proposed method significantly outperforms other state-of-the-art methods by up to 20\%. We open-source our training and testing code along with our pre-trained models: https://github.com/thohemp/6DRepNet.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Head Pose Estimation AFLW2000 6DRepNet MAE 3.97 # 10
Head Pose Estimation BIWI 6DRepNet MAE (trained with BIWI data) 2.66 # 3
MAE (trained with other data) 3.47 # 2
Head Pose Estimation Panoptic 6DRepNet Geodesic Error (GE) 8.08 # 3

Methods


No methods listed for this paper. Add relevant methods here