Xingran Zhou      周星然

Ph.D. student

Zhejiang University, Hangzhou City, P.R.China

Contact: xingranzh@zju.edu.cn


Biography

Xingran Zhou is a Ph.D. student at Zhejiang University, Hangzhou City, China. He is under the supervision of Professor Zhongfei Zhang.

He was a research intern at Microsoft Research Asia (MSRA) Visual Computing Group from July 2019 to November 2021. During his time at MSRA, he was mentored by Dr. Dong Chen.

His research interests focus on the intersection of Computer Vision and Computer Graphics. He is particularly interested in learning-based models for generating appealing visuals.


Publication

CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation


Xingran Zhou, Bo Zhang, Ting Zhang, Pan Zhang, Jianmin Bao, Dong Chen, Zhongfei Zhang, Fang Wen

CVPR 2021
Oral presentation (4.3% acceptance rate)
Best Paper Candidate (ID: 3592)

[Code]    [arXiv]    [pdf]    [BibTex]   
[Slides]    [Intro in Chinese]   

Text Guided Person Image Synthesis


Xingran Zhou, Siyu Huang, Yingming Li, Bin Li, Jiachen Li, Zhongfei Zhang

CVPR 2019 (acceptance rate 25.2%)

[arXiv]    [pdf]    [BibTex]

We present a novel method to manipulate the visual appearance (pose and attribute) of a person image according to natural language descriptions.

Generating Person Images with Appearance-aware Pose Stylizer


Siyu Huang, Haoyi Xiong, Zhi-Qi Cheng, Qingzhong Wang, Xingran Zhou, Bihan Wen, Jun Huan, Dejing Dou

International Joint Conference on Artificial Intelligence (IJCAI), 2020 (acceptance rate 12.6%)

[Code]    [arXiv]    [pdf]    [BibTex]

We present a novel generator called Appearance-aware Pose Stylizer (APS) which generates human images by coupling the target pose with the conditioned person appearance progressively.