Daniil-Osokin

Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.

Daniil-Osokin

Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.

Daniil-Osokin

Fast and accurate single-person pose estimation, ranked 10th at CVPR'19 LIP challenge. Contains implementation of "Global Context for Convolutional Pose Machines" paper.

Daniil-Osokin

Implementation of "Fully Learnable Group Convolution for Acceleration of Deep Neural Networks", CVPR'19

Daniil-Osokin