Liqian Ma's Homepage

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.

[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.

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]