My research uses machine learning to solve computer vision and graphics problems, with
a current focus on generative models, deformable 3D shape modeling, and their applications in creating realistic 3D virtual human models.
@article{prokudin2023dynamic,
title={Dynamic Point Fields},
author={Prokudin, Sergey and Ma, Qianli and Raafat, Maxime and Valentin, Julien and Tang, Siyu},
journal={arXiv preprint arXiv:2304.02626},
year={2023}
}
Explicit point-based representation + implicit deformation field = dynamic
surface models with instant inference and high quality geometry.
Robust single-scan animation of challenging clothing types even under extreme poses (see left figure).
@article{
zhang2023probabilistic,
title = {Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views},
author = {Siwei Zhang, Qianli Ma, Yan Zhang, Sadegh Aliakbarian, Darren Cosker, Siyu Tang},
booktitle = {arXiv preprint arXiv:2304.06024},
month = Apr,
year = {2023}
}
Reconstructing 3D human mesh from truncated/occluded egocentric view images in 3D environments:
our scene-conditioned diffusion model + collision score-guided sampling yields accurate pose estimation on observed
body parts & plausible, diverse generation of unobserved ones.
@inproceedings{SkiRT:3DV:2022,
title = {Neural Point-based Shape Modeling of Humans in Challenging Clothing},
author = {Ma, Qianli and Yang, Jinlong and Black, Michael J. and Tang, Siyu},
booktitle = {International Conference on 3D Vision (3DV)},
month = sep,
year = {2022},
}
The power of point-based digital human representations further unleashed: SkiRT models dynamic shapes of 3D clothed
humans including those that wear challenging outfits such as skirts and dresses.
@inproceedings{Egobody:ECCV:2022,
title = {{EgoBody}: Human Body Shape and Motion of Interacting People from Head-Mounted Devices},
author = {Zhang, Siwei and Ma, Qianli and Zhang, Yan and Qian, Zhiyin and Kwon, Taein and Pollefeys, Marc and Bogo, Federica and Tang, Siyu},
booktitle = {European Conference on Computer Vision (ECCV)},
month = oct,
year = {2022}
}
A large-scale dataset of accurate 3D body shape, pose and motion of humans interacting in 3D scenes,
with multi-modal streams from third-person and egocentric views, captured by Azure Kinects and a HoloLens2.
@inproceedings{POP:ICCV:2021,
title = {The Power of Points for Modeling Humans in Clothing},
author = {Ma, Qianli and Yang, Jinlong and Tang, Siyu and Black, Michael J.},
booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
pages = {10974--10984},
month = oct,
year = {2021},
}
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.
@inproceedings{MetaAvatar:NeurIPS:2021,
title = {{MetaAvatar}: Learning Animatable Clothed Human Models from Few Depth Images},
author={Wang, Shaofei and Mihajlovic, Marko and Ma, Qianli and Geiger, Andreas and Tang, Siyu},
journal={Advances in Neural Information Processing Systems},
volume={34},
pages={2810--2822},
year={2021},
}
Creating an avatar of unseen subjects from as few as eight monocular depth images using a meta-learned, multi-subject, articulated,
neural signed distance field model for clothed humans.
@inproceedings{SCALE:CVPR:2021,
title = {{SCALE}: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements},
author = {Ma, Qianli and Saito, Shunsuke and Yang, Jinlong and Tang, Siyu and Black, Michael J.},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
pages = {16082-16093},
year = {2021},
month = jun,
}
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.
@inproceedings{SCANimate:CVPR:2021,
title={{SCANimate}: Weakly Supervised Learning of Skinned Clothed Avatar Networks},
author={Saito, Shunsuke and Yang, Jinlong and Ma, Qianli and Black, Michael J},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
pages={2886--2897},
year={2021},
month=jun,
}
Cycle-consistent implicit skinning fields + locally pose-aware implicit function = a
fully animatable avatar with implicit surface from raw scans without surface registration.
@inproceedings{PLACE:3DV:2020,
title = {{PLACE}: Proximity Learning of Articulation and Contact in {3D} Environments},
author = {Zhang, Siwei and Zhang, Yan and Ma, Qianli and Black, Michael J. and Tang, Siyu},
booktitle = {International Conference on 3D Vision (3DV)},
month = nov,
year = {2020},
}
An explicit representation for 3D person-scene contact relations that enables
automated synthesis of realistic humans posed naturally in a given scene.
inproceedings{CAPE:CVPR:20,
title = {Learning to Dress {3D} People in Generative Clothing},
author = {Ma, Qianli and Yang, Jinlong and Ranjan, Anurag and Pujades, Sergi and Pons-Moll, Gerard and Tang, Siyu and Black, Michael J.},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
pages={6468-6477},
month = jun,
year = {2020},
}
CAPE — a graph-CNN-based generative model and a large-scale dataset
for 3D human meshes in clothing in varied poses and garment types.