I am an Associate Professor in the Faculty of Computing at Harbin Institute of Technology (HIT). I received my bachelor's degree in 2013 and Ph.D. degree in 2019 from HIT, under the supervision of Prof. Wangmeng Zuo.

From July 2025 to July 2026, I was a visiting scholar in the Visual Understanding and Generation (VUG) Laboratory at the School of Computing and Information Systems, Singapore Management University, hosted by Prof. Shengfeng He. From October 2016 to October 2017, I was a visiting scholar at University of California, Merced, supervised by Prof. Ming-Hsuan Yang.

My research interests span computer vision, visual generation and editing, visual understanding, and low-level vision tasks. I have published over 40 papers in leading conferences and journals, including IEEE T-PAMI, T-IP, T-NNLS, CVPR, and ECCV.

🎓 For Prospective Students

We are constantly seeking motivated Ph.D./master students to join our team. If you are interested in the related research topics, welcome to drop an email.

🔥 News

2026.08 — 🎉 One paper was accepted by TMM 2026.
2026.08 — 😊 I completed my visit at SMU and returned to HIT.
2026.06 — 🎉 One paper was accepted by ECCV 2026.
2026.04 — 🎉 Three papers were accepted by CVPR 2026, including one Oral paper.
2025.06 — 🎉 One paper was accepted by ICME 2025.
2024.09 — 🎉 One paper was accepted by IJCV.

📝 Publications

Publications are listed below. Please see my Google Scholar profile for the latest citation information. * indicates the corresponding author.

Drive-AdaDiT: Adapting DiT with Hybrid Attention for Multi-View Driving Scene Video Generation

Xiaohe Wu, Hannan Lu, Jiawei Zhang, Xiameng Qin, Dongwei Ren, Xinyu Zhang, Wangmeng Zuo

IEEE TMM 2026

🎓 For Prospective Students

🔥 News

📝 Publications

Drive-AdaDiT: Adapting DiT with Hybrid Attention for Multi-View Driving Scene Video Generation

Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation

SelfHVD: Self-Supervised Handheld Video Deblurring for Mobile Phones

S2AM3D: Scale-controllable Part Segmentation of 3D Point Cloud

CREval: An Automated Interpretable Evaluation for Creative Image Manipulation under Complex Instructions

DeAltHDR: Learning HDR Video Reconstruction from Degraded Alternating Exposure Sequences

I2V-Adapter: Fast Adapting Image Pre-trained Models for Video Correspondence

DeblurDiff: Real-World Image Deblurring with Generative Diffusion Models

MC^2: Multi-concept Guidance for Customized Multi-concept Generation

Generative Inbetweening through Frame-wise Conditions-driven Video Generation

Image Demoiréing Using Dual Camera Fusion on Mobile Phones

Reblurring-Guided Single Image Defocus Deblurring: A Learning Framework with Misaligned Training Pairs

An Open-set Semi-Supervised Contrastive Learning for Bearing Fault Diagnosis

Learning Real-World Image De-weathering with Imperfect Supervision

Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser

Degraded Structure and Hue Guided Auxiliary Learning for Low-Light Image Enhancement

Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learning

Invertible Network for Unpaired Low-Light Image Enhancement

Learning Diverse Tone Styles for Image Retouching

Survey on Leveraging Pre-trained Generative Adversarial Networks for Image Editing and Restoration

On Better Detecting and Leveraging Noisy Samples for Learning with Severe Label Noise

Inferring and Leveraging Parts from Object Shape for Improving Semantic Image Synthesis

Benchmark Dataset and Effective Inter-Frame Alignment for Real-World Video Super-Resolution

Unidirectional Video Denoising by Mimicking Backward Recurrent Modules with Look-Ahead Forward Ones

Unpaired Learning of Deep Image Denoising

Remove Cosine Window from Correlation Filter-based Visual Trackers: When and How

Learning Second-order Statistics for Place Recognition Based on Robust Covariance Estimation of CNN Features

Learning Support Correlation Filters for Visual Tracking

Joint Learning of Siamese Network with Top-down Modulation and Hard Example Mining for Visual Tracking

Joint Representation and Truncated Inference Learning for Correlation Filter Based Tracking

VITAL: VIsual Tracking via Adversarial Learning

Learning Siamese Network with Top-Down Modulation for Visual Tracking

F-SVM: Combination of Feature Transformation and SVM Learning via Convex Relaxation

L-SVM: A Radius-margin-based SVM Algorithm with LogDet Regularization

Learning Pairwise SVM on Hierarchical Deep Features for Ear Recognition

Learning Pairwise SVM on Deep Features for Ear Recognition

Radius-margin Based Support Vector Machine with LogDet Regularization

🎖 Honors & Awards

💬 Invited Talks

🤝 Academic Services

📖 Teaching

🎓 Education & Work Experience