profile picture

Tianxiang Ma

Postgraduate student @ University of Chinese Academy of Sciences

image & video synthesis

deep generative models

3d computer vision

recitfying

inversion

edting

applications

3

presentations

SHORT BIO

I am a Ph.D. Candidate of CRIPAC (led by Prof. Tieniu Tan), National Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences (CASIA) under the supervision of Prof. Tieniu Tan and Prof. Jing Dong. Before that, I received my Bachelor degree from Zhengzhou University (ZZU) in 2019 under the supervision of Prof. Ronghui Luo and Dr. Yongzhi Tian. My current research interests mainly lie in the fields of deep learning, especially applying generative adversarial models to computer vision.

Presentations

CFFT-GAN: Cross-domain Feature Fusion Transformer for Exemplar-based Image Translation

Tianxiang Ma and 5 other authors

Semantic 3D-aware Portrait Synthesis and Manipulation Based on Compositional Neural Radiance Field

Tianxiang Ma and 4 other authors

ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing

Bingchuan Li and 6 other authors