Hello I'm

Wei Liu

I am currently a research scientist at ByteDance Inc. I received my bachelor and Ph.D. from Harbin Institute of Technology, Harbin, China in 2016 and 2020, respectively. From 2017 to 2019, I was a visiting student at the Ohio State University, Columbus, USA. My main research interests include: Computer Vision, Content/Image Generation, Multimodal Generation, Image Enhancement and Domain Adaptation.

  liuwei.jikun@bytedance.com   |      

Projects

Font Generative, Multimodal Generation
XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation

Wei Liu, Fangyue Liu, Fei Ding, Qian He, Zili Yi

CVPR, 2022

Image Enhancement, Denoising
Densely self-guided wavelet network for image denoising

Wei Liu, Yuzhi Zhao, Qiong Yan

CVPR Workshop, 2020

AIGC, Diffusion model
DreamTuner: Single Image is Enough for Subject-Driven Generation

Miao Hua, Jiawei Liu, Fei Ding, Wei Liu

AIGC, Diffusion Model
DreamIdentity: Improved Editability for Efficient Face-identity Preserved Image Generation

Zhuowei Chen, Shancheng Fang, Wei Liu

AAAI, 2024

AIGC, Diffusion Model
Design Booster: A Text-Guided Diffusion Model for Image Translation with Spatial Layout Preservation

Shiqi Sun, Shancheng Fang, Qian He, Wei Liu

AIGC, GAN, Smart Edit
CFFT-GAN: Cross-domain Feature Fusion Transformer for Exemplar-based Image Translation

Tianxiang Ma, Bingchuan Li, Wei Liu

Experience

Education
Harbin Institute of Technology

Bachelor, PhD, 2012-2020

Topic: Image Generation, Domain Adaptation, Semantic Segmentation

Internship
SenseTime MIG

Research Intern, 2019-2020

Topic: Image Enhancement, Image Denoising, Image Deglow, Image Generation

Research Scientist
ByteDance Inc.

2020 to present

Topic: Content Generation, Multimodal Generation, Smart Editing, Smart Design

Education
The Ohio State University

Visiting student, 2017-2019

Topic: Domain Adaptation, Stereo Matching, Semantic Segmentation

Publications

Image Generation

Image Enhancement

Domain Adaptation

Stereo Matching

Others

Honor

                                      NTIRE 2020 Spectral Reconstruction Challenge Real World Track 1st place (1/95)
                                      2020 IEEE GRSS Data Fusion Contest Global Land Cover Mapping with Weak Supervision 1st place (1/169)
                                      2019 IEEE GRSS Data Fusion Contest Pairwise Semantic Stereo Challenge 2nd place (2/144)
                                      2019 IEEE GRSS Data Fusion Contest Multiview Semantic Stereo Challenge 2nd place (2/123)