Researcher · Computer Vision · Generative Models

Zhenyao Wu

Working at the intersection of generative image editing, graphic generative models, multimodal models, low-level vision, and robust visual understanding.

About

Research built around practical visual intelligence.

I am currently a researcher at Honor Device Co., Ltd.. My research interests include generative image editing, graphic generative models, multimodal models, and low-level vision.

Before joining Honor, I received my Ph.D. degree from University of South Carolina under the supervision of Prof. Song Wang and Prof. Lili Ju in 2022. Before that, I received my B.S. in College of Intelligence and Computing from Tianjin University in 2018.

I am looking for full-time researchers and interns on low-level vision, graphic generative models, and multimodal models. Feel free to send me an email if you are interested.

News

Recent updates

One paper accepted at CVPR 2025.

Two papers accepted at AAAI 2023.

Four papers accepted at ECCV 2022.

One paper accepted at ACMMM 2022.

One paper accepted at TPAMI.

Selected Publications

Vision, adaptation, saliency, and depth.

Domain adaptation network publication thumbnail

TPAMI

A One-Stage Domain Adaptation Network with Image Alignment for Unsupervised Nighttime Semantic Segmentation

Xinyi Wu, Zhenyao Wu, Lili Ju, Song Wang.

PDF Code
SM-PPM publication thumbnail

AAAI 2022

Style Mixing and Patchwise Prototypical Matching for One-Shot Unsupervised Domain Adaptive Semantic Segmentation

Xinyi Wu, Zhenyao Wu, Yuhang Lu, Lili Ju, Song Wang.

PDF Code
DANNet publication thumbnail

CVPR 2021 Oral

DANNet: A One-Stage Domain Adaption Network for Unsupervised Nighttime Semantic Segmentation

Zhenyao Wu, Xinyi Wu, Hao Guo, Lili Ju, Song Wang.

PDF Code
Shadow generation and removal publication thumbnail

CVPR 2021

From Shadow Generation to Shadow Removal

Zhihao Liu, Hui Yin, Xinyi Wu, Zhenyao Wu, Yang Mi, Song Wang.

PDF Code
Binaural audio-visual localization thumbnail

AAAI 2021

Binaural Audio-Visual Localization

Xinyi Wu, Zhenyao Wu, Lili Ju, Song Wang.

PDF Data
SalSAC publication thumbnail

AAAI 2020

SalSAC: A Video Saliency Prediction Model with Shuffled Attentions and Correlation-based ConvLSTM

Xinyi Wu, Zhenyao Wu, Jinglin Zhang, Lili Ju, Song Wang.

PDF
SC-GAN depth learning publication thumbnail

ICCV 2019

Spatial Correspondence with Generative Adversarial Network: Learning Depth from Monocular Videos

Zhenyao Wu, Xinyi Wu, Xiaoping Zhang, Song Wang, Lili Ju.

PDF Results
Semantic stereo matching publication thumbnail

ICCV 2019

Semantic Stereo Matching with Pyramid Cost Volumes

Zhenyao Wu, Xinyi Wu, Xiaoping Zhang, Song Wang, Lili Ju.

PDF Results

Experience & Service

Academic and industry practice.

Internships

Applied Scientist Intern, Amazon, New York, NY. May-Nov, 2021. Worked with Sonny Hu, Dr. Amit Agrawal, and Dr. Larry Davis.

Service

Program Committee/Reviewer: CVPR(2020/2021/2022/2023), ICCV(2021), ECCV(2022), AAAI(2020/2021/2022/2023), NeurIPS(2020/2021/2022/2023), ICLR(2021), IJCAI(2022), ACMMM(2022), WACV(2020/2021), ACCV(2020), IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Multimedia, IEEE Transactions on Image Processing, Pattern Recognition Letters, IET Computer Vision.

Get In Touch

Open to research collaborations and recruiting conversations.

Personal space