QuaterNet: A Quaternion-based Recurrent Model for Human Motion
Deep learning for predicting or generating 3D human pose sequences is an active research area. Previous work regresses either joint rotations or joint positions. The former strategy is prone to error accumulation along the kinematic chain, as well as discontinuities when using Euler angle or exponential map parameterizations. The latter requires re-projection onto skeleton constraints to avoid bone stretching and invalid configurations. This work addresses both limitations. Our recurrent network, QuaterNet, represents rotations with quaternions and our loss function performs forward kinematics on a skeleton to penalize absolute position errors instead of angle errors. On short-term predictions, QuaterNet improves the state-of-the-art quantitatively. For long-term generation, our approach is qualitatively judged as realistic as recent neural strategies from the graphics literature.
Code (1)
Tasks
3D Human Pose EstimationMotion EstimationPositionSimilar Papers 제목 키워드 기반
Modeling Human Motion with Quaternion-based Neural Networks
Previous work on predicting or generating 3D human pose sequences regresses either joint rotations or joint positions. The former strategy is prone to error accumulation along the kinematic chain, as well as discontinuit…
PVRED: A Position-Velocity Recurrent Encoder-Decoder for Human Motion Prediction
Human motion prediction, which aims to predict future human poses given past poses, has recently seen increased interest. Many recent approaches are based on Recurrent Neural Networks (RNN) which model human poses with e…
DecoderHuman motion predictionmotion predictionPosition+1Quaternion recurrent neural network with real-time recurrent learning and maximum correntropy criterion
We develop a robust quaternion recurrent neural network (QRNN) for real-time processing of 3D and 4D data with outliers. This is achieved by combining the real-time recurrent learning (RTRL) algorithm and the maximum cor…
motion predictionQuaMo: Quaternion Motions for Vision-based 3D Human Kinematics Capture
Vision-based 3D human motion capture from videos remains a challenge in computer vision. Traditional 3D pose estimation approaches often ignore the temporal consistency between frames, causing implausible and jittery mot…
3D Pose EstimationQuaternion-Valued Recurrent Projection Neural Networks on Unit Quaternions
Hypercomplex-valued neural networks, including quaternion-valued neural networks, can treat multi-dimensional data as a single entity. In this paper, we present the quaternion-valued recurrent projection neural networks …