Liqian Ma (马里千)


Algorithm Head
ZMO AI Inc.
Email: LiqianMa dot Scholar at outlook dot com

 

[CV]   [GitHub]   [Google Scholar]   [Semantic Scholar]   [Linkedin]

 


Biography

I am the algorithm head at ZMO.AI and lead the R&D team for AIGC. I obtained my PhD degree at VISICS group of KU Leuven supervised by Prof. Luc Van Gool. Before this, I obtained my Master's and Bachelor's degree from Peking University and South China University of Technology. My research goal is to develop a creative self-learning AI system. Currently, I am working on image/video understanding and synthesis. Please contact me if you are interested in collaboration or internship/fulltime positions.

 

News

[2024.01] Our work "StableIdentity: Inserting Anybody into Anywhere at First Sight" is on the arXiv.

[2024.01] Our paper "PTUS: Photo-Realistic Talking Upper-Body Synthesis via 3D-Aware Motion Decomposition Warping" is accepted by AAAI 2024.

[2023.10] Our paper "Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing" is accepted by ICCV 2023.

[2023.02] Our paper "GM-NeRF: Learning Generalizable Model-based Neural Radiance Fields from Multi-view Images" is accepted by CVPR 2023.

[2022.08] Our paper "Controllable Radiance Fields for Dynamic Face Synthesis" is accepted by 3DV 2022.

[2022.08] Our paper "UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation" is accepted by ECCV 2022.

[2022.08] We won the Third Place Award in the WCPA Challenge Body Track of ECCV 2022.


 

Publications

 

StableIdentity: Inserting Anybody into Anywhere at First Sight

Qinghe Wang,  Xu Jia,  Xiaomin Li,  Taiqing Li,  Liqian Ma Yunzhi Zhuge,  Huchuan Lu 

ArXiv, 2024

 

[Project]  [Code]  [Paper]  [BibTex]

 

PTUS: Photo-Realistic Talking Upper-Body Synthesis via 3D-Aware Motion Decomposition Warping

Luoyang Lin,  Zutao Jiang,  Xiaodan Liang,  Liqian Ma Michael C. Kampffmeyer,  Xiaochun Cao, 

AAAI, 2024

 

[Project come soon]  [Code come soon]  [Paper]  [BibTex]

 

Cloth2Body: Generating 3D Human Body Mesh from 2D Clothing

Lu Dai,  Liqian Ma Shenhan Qian,  Hao Liu,  Ziwei Liu,  Hui Xiong, 

ICCV, 2023

 

[Project]  [Code come soon]  [Paper]  [BibTex]

 

GM-NeRF: Learning Generalizable Model-based Neural Radiance Fields from Multi-view Images

Jianchuan Chen*,  Wentao Yi*,  Liqian Ma Xu Jia,  Huchuan Lu 

(*denotes equal contribution)

CVPR, 2023

 

[Project]  [Video]  [Paper]  [Arxiv] 

UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation

Shenhan Qian,  Jiale Xu,  Ziwei Liu,  Liqian Ma Shenghua Gao 

ECCV, 2022

 

[Project]  [Code]  [Paper]

Pixel2ISDF: Implicit Signed Distance Fields based Human Body Model from Multi-view and Multi-pose Images

Jianchuan Chen,  Wentao Yi,  Tiantian Wang,  Xing Li,  Liqian Ma Yangyu Fan,  Huchuan Lu 

Third Place Award in WCPA Challenge Body Track, ECCV, 2022

 

[Paper] 

Controllable Radiance Fields for Dynamic Face Synthesis

Peiye Zhuang,  Liqian Ma Sanmi Koyejo,  Alexander G. Schwing 

3DV, 2022

 

[Project]  [Code]  [Paper]

Direct Dense Pose Estimation

Liqian Ma Lingjie Liu,  Christian Theobalt,  Luc Van Gool 

3DV, 2021

 

[Project]  [Paper]   [BibTex]

FoV-Net: Field-of-View Extrapolation Using Self-Attention and Uncertainty

Liqian Ma Stamatios Georgoulis,  Xu Jia,  Luc Van Gool 

RA-L & ICRA, 2021

 

[Project]  [Paper]   [BibTex]

Unselfie: Translating Selfies to Neutral-pose Portraits in the Wild

Liqian Ma Zhe Lin,  Connelly Barnes,  Alexei A. Efros,  Jingwan Lu, 

ECCV, 2020

 

[Project]  [Paper]  [ArXiv]  [BibTex]

Unpaired Image Shape Translation Across Fashion Data

Kaili Wang*,  Liqian Ma*,  José Oramas M.,  Luc Van Gool  Tinne Tuytelaars

(*denotes equal contribution)

ICIP, 2020, Best Paper Awards Finalist

 

[Paper] [BibTex]

A Novel BiLevel Paradigm for Image-to-Image Translation

Liqian Ma Qianru Sun,  Bernt Schiele,  Luc Van Gool 

ArXiv, 2019

 

[Paper] [ArXiv] [BibTex]

 

Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency

Liqian Ma Xu Jia,  Stamatios Georgoulis,  Tinne Tuytelaars,  Luc Van Gool 

ICLR, 2019

 

[Project]  [Code]  [Paper] [ArXiv] [BibTex]

 

Customized Multi-Person Tracker

Liqian Ma*,  Siyu Tang*,  Michael J. Black,  Luc Van Gool 

(*denotes equal contribution)

Asian Conference on Computer Vision (ACCV Oral), 2018

 

[Paper]  [BibTex]

 

Disentangled Person Image Generation

Liqian Ma Qianru Sun,  Stamatios Georgoulis,  Luc Van Gool,  Bernt Schiele,  Mario Fritz 

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR Spotlight), 2018

 

[Project] [Code] [Paper] [ArXiv] [BibTex]

 

Natural and Effective Obfuscation by Head Inpainting

Qianru Sun*,  Liqian Ma*,  Seong Joon Oh,  Luc Van Gool,  Bernt Schiele,  Mario Fritz 

(*denotes equal contribution)

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018

 

[Code] [Paper] [ArXiv] [BibTex]

 

Pose Guided Person Image Generation

Liqian Ma Xu Jia*,  Qianru Sun*,  Tinne Tuytelaars,  Bernt Schiele,  Luc Van Gool 

(*denotes equal contribution)

In Neural Information Processing Systems (NIPS), 2017

 

[Project] [Code] [Paper] [ArXiv] [Slides] [BibTex]

 

Orientation Driven Bag of Appearances for Person Re-identification

Liqian Ma Hong Liu,  Liang Hu,  Can Wang,  Qianru Sun 

ArXiv, 2016

 

[Paper] [ArXiv] [BibTex]

 

A novel hierarchical Bag-of-Words model for compact action representation

Qianru Sun,  Hong Liu,  Liqian Ma

Neurocomputing, 2016

 

[Paper] [BibTex]

 

Online person orientation estimation based on classifier update

Hong Liu,  Liqian Ma

In IEEE International Conference on Image Processing (ICIP Oral), 2015

 

[Paper] [BibTex]

 

Body-structure based feature representation for person re-identification

Hong Liu,  Liqian Ma Can Wang, 

In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015

 

[Paper] [BibTex]

 

Depth Motion Detection—A Novel RS-Trigger Temporal Logic based Method

Can Wang,  Hong Liu,  Liqian Ma

IEEE Signal Processing Letters (SPL), 2014

 

[Paper] [BibTex]

 

Academic service