Zhonghua Wu

About Me

Zhonghua Wu is currently a Researcher at SenseTime Research Singapore. Prior to that, he completed his PhD at the School of Computer Science and Engineering, Nanyang Technological Unversity, supervised by Prof. Cai Jianfei and Prof. Lin Guosheng. Previously, he recieved a bachlor degree from College of Electronic Engineering (EE) at University of Electronic Science and Technology of China (UESTC).

His research interests are broadly in computer vision, with a focus on multimodal large language models (MLLM), unified understanding and generation models, AI-generated content (AIGC), image restoration, visual understanding etc.

He serves as Area Chair for CVPR and ICLR.

Experiences

Algorithm Researcher | SenseTime International
Nov 2022 - Now

Reseach Assistant | Nanyang Technological University
Nov 2017 - Nov 2022

Algorithm Researcher Intern | Minieye
Aug 2017 - Oct 2017

Main Publications [Google Scholar]

Next Visual Granularity Generation
Yikai Wang, Zhouxia Wang, Zhonghua Wu, Qingyi Tao, Kang Liao, Chen Change Loy
Preprint, 2025
[arXiv] [Code] [Project Page]

OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation
Size Wu*, Zhonghua Wu*, Zerui Gong*, Qingyi Tao, Sheng Jin, Qinyue Li, Wei Li, Chen Change Loy
(* indicates equal contribution)
arXiv preprint, 2025
[arXiv] [GitHub]

Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentation
Lechun You, Zhonghua Wu, Weide Liu, Xulei Yang, Jun Cheng, Wei Zhou, Bharadwaj Veeravalli, Guosheng Lin
arXiv preprint, 2025
[arXiv]

Codebrain: Impute any brain mri via instance-specific scalar-quantized codes
Yicheng Wu, Tao Song, Zhonghua Wu, Zongyuan Ge, Zhaolin Chen, Jianfei Cai
arXiv preprint, 2025
[arXiv]

SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfer
Zerui Gong, Zhonghua Wu, Qingyi Tao, Qinyue Li, Chen Change Loy
International Conference on Computer Vision (ICCV), 2025
[arXiv] [GitHub]

Harmon: Harmonizing Visual Representations for Unified Multimodal Understanding and Generation
Size Wu, Wenwei Zhang, Lumin Xu, Sheng Jin, Zhonghua Wu, Qingyi Tao, Wentao Liu, Wei Li, Chen Change Loy
International Conference on Computer Vision (ICCV), 2025
[arXiv] [GitHub] [Project Page]

MOWA: Multiple-in-One Image Warping Model
Kang Liao, Zongsheng Yue, Zhonghua Wu, Chen Change Loy
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
[arXiv] [Project Page] [Code]

IPVTON: Image-based 3D Virtual Try-on with Image Prompt Adapter
Xiaojing Zhong, Zhonghua Wu, Xiaofeng Yang, Guosheng Lin, Qingyao Wu
AAAI Conference on Artificial Intelligence, 2025
[arXiv]

Weakly Supervised Segmentation on Outdoor 4D Point Clouds With Progressive 4D Grouping
Hanyu Shi, Fayao Liu, Zhonghua Wu, Yi Xu, Guosheng Lin
IEEE Transactions on Pattern Analysis and Machine Intelligence

Reliability-Adaptive Consistency Regularization for Weakly-Supervised Point Cloud Segmentation
Zhonghua Wu, Yicheng Wu, Guosheng Lin, Jianfei Cai
International Journal of Computer Vision, 2024
[arXiv] [Code]

Aware Visual Grounding in 3D Scenes
Xiangxi Shi, Zhonghua Wu, Stefan Lee
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024
[arXiv]

Modeling continuous motion for 3D point cloud object tracking
Zhipeng Luo, Gongjie Zhang, Changqing Zhou, Zhonghua Wu, Qingyi Tao, Lewei Lu, Shijian Lu
Proceedings of the AAAI Conference on Artificial Intelligence, 2024
[arXiv]

Harmonizing base and novel classes: A class-contrastive approach for generalized few-shot segmentation
Weide Liu, Zhonghua Wu, Yang Zhao, Yuming Fang, Chuan-Sheng Foo, Jun Cheng, Guosheng Lin
International Journal of Computer Vision, 2024
[arXiv] [Code]

LCReg: Long-tailed image classification with latent categories based recognition
Weide Liu, Zhonghua Wu, Yiming Wang, Henghui Ding, Fayao Liu, Jie Lin, Guosheng Lin
Pattern Recognition, 2024
[arXiv]

Towards robust and expressive whole-body human pose and shape estimation
Hui En Pang, Zhongang Cai, Lei Yang, Qingyi Tao, Zhonghua Wu, Tianwei Zhang, Ziwei Liu
Advances in Neural Information Processing Systems, 2023
[arXiv] [Code]

Coactseg: Learning from heterogeneous data for new multiple sclerosis lesion segmentation
Yicheng Wu, Zhonghua Wu, Hengcan Shi, Bjoern Picker, Winston Chong, Jianfei Cai
International Conference on Medical Image Computing and Computer-Assisted Intervention, 2023
[arXiv]

DI-Net: Decomposed Implicit Garment Transfer Network for Digital Clothed 3D Human
Xiaojing Zhong, Yukun Su, Zhonghua Wu, Guosheng Lin, Qingyao Wu
arXiv preprint, 2023
[arXiv]

Sara: Controllable makeup transfer with spatial alignment and region-adaptive normalization
Xiaojing Zhong, Xinyi Huang, Zhonghua Wu, Guosheng Lin, Qingyao Wu
arXiv preprint, 2023
[arXiv]

Exploring Smoothness and Class-Separation for Semi-supervised Medical Image Segmentation
Yicheng Wu, Zhonghua Wu, Qianyi Wu, Zongyuan Ge, Jianfei Cai
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2022
[arXiv] [Code]

Dual Adaptive Transformations for Weakly Supervised Point Cloud Segmentation
Zhonghua Wu, Yicheng Wu, Guosheng Lin, Jianfei Cai, Chen Qian
European Conference on Computer Vision (ECCV), 2022
[arXiv] [Code]

Learning Meta-class Memory for Few-Shot Semantic Segmentation
Zhonghua Wu, Xiangxi Shi, Guosheng Lin, Jianfei Cai
International Conference on Computer Vision (ICCV), 2021
[arXiv] [Code]

MV-TON: Memory-based Video Virtual Try-on network
Xiaojing Zhong*, Zhonghua Wu*, Taizhe Tan, Guosheng Lin, Qingyao Wu
(* indicates equal contribution)
ACM International Conference on Multimedia (ACM MM), 2021
[arXiv]

Portable Food‐Freshness Prediction Platform Based on Colorimetric Barcode Combinatorics and Deep Convolutional Neural Networks
Lingling Guo, Ting Wang, Zhonghua Wu, Jianwu Wang, Ming Wang, Zequn Cui, Shaobo Ji, Jianfei Cai, Chuanlai Xu, Xiaodong Chen
Advanced Materials
[Wiley Online Library]

Exploring Bottom-up and Top-down Cues with Attentive Learning for Webly Supervised Object Detection
Zhonghua Wu, Qingyi Tao, Guosheng Lin, Jianfei Cai
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020
[arXiv]

M2E-Try On Net: Fashion from Model to Everyone
Zhonghua Wu, Guosheng Lin, Qingyi Tao, Jianfei Cai
ACM International Conference on Multimedia (ACM MM), 2019
[arXiv]