no code implementations • ICCV 2023 • Mingyi Shi, Sebastian Starke, Yuting Ye, Taku Komura, Jungdam Won
We present a novel motion prior, called PhaseMP, modeling a probability distribution on pose transitions conditioned by a frequency domain feature extracted from a periodic autoencoder.
no code implementations • ICCV 2021 • Jingyuan Liu, Mingyi Shi, Qifeng Chen, Hongbo Fu, Chiew-Lan Tai
We present a novel approach for extracting human pose features from human action videos.
no code implementations • 22 Jun 2020 • Mingyi Shi, Kfir Aberman, Andreas Aristidou, Taku Komura, Dani Lischinski, Daniel Cohen-Or, Baoquan Chen
We introduce MotioNet, a deep neural network that directly reconstructs the motion of a 3D human skeleton from monocular video. While previous methods rely on either rigging or inverse kinematics (IK) to associate a consistent skeleton with temporally coherent joint rotations, our method is the first data-driven approach that directly outputs a kinematic skeleton, which is a complete, commonly used, motion representation.
no code implementations • 21 Aug 2018 • Kfir Aberman, Mingyi Shi, Jing Liao, Dani Lischinski, Baoquan Chen, Daniel Cohen-Or
After training a deep generative network using a reference video capturing the appearance and dynamics of a target actor, we are able to generate videos where this actor reenacts other performances.
2 code implementations • 10 May 2018 • Kfir Aberman, Jing Liao, Mingyi Shi, Dani Lischinski, Baoquan Chen, Daniel Cohen-Or
Correspondence between images is a fundamental problem in computer vision, with a variety of graphics applications.