Qianli Ma

I am a PhD student at the Max Planck Institute for Intelligent Systems and ETH Zürich, co-supervised by Michael Black and Siyu Tang . I am also associated to the Max Planck ETH Center for Learning Systems. Prior to this, I received my Master's degree in Optics and Photonics from Karlsruhe Institute of Technology and Bachelor's degree in Physics from Peking University.

My research uses machine learning to solve computer vision and graphics problems, with a current focus on 3D representations and deformable 3D shape modeling.

Email  /  Google Scholar  /  Twitter  /  Github

POP — a point-based, unified model for multiple subjects and outfits that can turn a single, static 3D scan into an animatable avatar with natural pose-dependent clothing deformations.

A multi-subject, articulated, neural signed distance field model for clothed humans, which can fast create an avatar of unseen subjects from as few as 8 monocular depth images.

Modeling pose-dependent shapes of clothed humans explicitly with hundreds of articulated surface elements: the clothing deforms naturally even in the presence of topological change.

Creating an avatar with pose-dependent clothing deformation from raw scans without template surface registration.

An explicit representation for 3D person-​scene contact relations that enables automated synthesis of realistic humans posed naturally in a given scene.

CAPE — a graph-CNN-based generative model and a large-scale dataset for 3D human meshes in clothing in varied poses and garment types.