PhD Internship - Remote

Summary

Meshcapade is focused on creating intelligent humanoids in the 3D world, and they are seeking a PhD Intern to assist in developing motion tracking algorithms. The role involves creating workflows, developing algorithms, and evaluating performance in the context of human motion capture.

Responsibilities

• Creating a workflow to transfer motions from SMPL-X to humanoids (e.g. Unitree G1) in simulation
• Developing an algorithm to perform cross-embodiment motion tracking
• Evaluating the performance of the tracking algorithm
• Combining generating motion models (e.g. diffusion models) to the tracking algorithm

Skills

• Knowledge of PyTorch, deep learning, neural networks, C++
• Knowledge of good software development practice, e.g. git, documentation
• Knowledge of reinforcement learning and robot physical simulation
• Knowledge of SMPL, SMPL-X, or character animation
• At least one paper in CVPR/ICCV/ECCV/IROS/ICRA or equivalent

Qualifications

Must Haves

• Knowledge of PyTorch, deep learning, neural networks, C++
• Knowledge of good software development practice, e.g. git, documentation
• Knowledge of reinforcement learning and robot physical simulation
• Knowledge of SMPL, SMPL-X, or character animation
• At least one paper in CVPR/ICCV/ECCV/IROS/ICRA or equivalent

Benefits

• Research experiences both in academia and industry.
• Possibility of paper publication.
• 6-months working contract.
• Flexible remote work with global availability