Research Projects

DCT-Net: Domain-Calibrated Translation for Portrait Stylization

Y. Men, Y. Yao, M. Cui, Z. Lian and X. Xie

This paper introduces DCT-Net, a novel image translation architecture for few-shot portrait stylization, enabling advanced ability to high-preserving contents, strong generality to complicated real-world scenes, and high scalability to full-body translation with only head observations.
Project Page Paper Code Demo Video

Unpaired Cartoon Image Synthesis via Gated Cycle Mapping

CVPR 2022
Y. Men, Y. Yao, M. Cui, Z. Lian, X. Xie and X. Hua

A common cartoon translator which can not only simultaneously render exaggerated anime faces and realistic cartoon scenes, but also provide flexible user controls for desired cartoon styles.
Project Page PDF Demo Video

Controllable Person Image Synthesis with Attribute-Decomposed GAN

CVPR 2020
Y. Men, Y. Mao, Y. Jiang, W. Ma and Z. Lian

This paper introduces Attribute-Decomposed GAN, a novel generative model for controllable person image synthesis, which can produce realistic person images with desired human attributes (e.g., pose, head, upper clothes and pants) provided in various source inputs.
Project Page PDF Code Demo Video

DynTypo: Example-based Dynamic Text Effects Transfer

CVPR 2019
Y. Men, Z. Lian, Y. Tang, and J. Xiao

In this paper, we present a novel approach for dynamic text effects transfer by using example-based texture synthesis and high-quality results with temporal smoothing and sophisticated dynamic effects are acqired.
Project Page PDF Demo Video

A Common Framework for Interactive Texture Transfer

CVPR 2018
Y. Men, Z. Lian, Y. Tang, and J. Xiao

In this paper, we present a general-purpose solution to interactive texture transfer problems including turning doodles into artworks, editing decorative patterns, generating texts in special effect as well as controlling effect distribution in text images, and swapping textures.
PDF Project Page Poster

High Precision Gesture Sensing via Quantitative Characterization of the Doppler Effect

ICPR 2016
H. Ai, Y. Men*, L. Han, Z. Li, and M. Liu

This paper presents a high precision gesture recognition system that leverages the Doppler effect of ultrasound to sense in-air hand gestures. The system can precisely identify a wider variety of gestures than other systems without any modification to consumer laptops.
PDF Project Page

Course Projects

Ultrasonic Doppler-based Human-computer Interaction System

2016 - 2017 Fall

Implemented an HCI system using gesture sensing for 3D-characters control, album flip, etc.
— the core algorithm for doppler-based gesture recognition
— 3D character controlling using Unity3D
— UI design and code programming with C#
=> Back to my personal website<=