Visual Computing Lab at PolyU · Hung Hom

Advancing
Visual Intelligence
for a Better World.

We are a research lab at The Hong Kong Polytechnic University led by Chair Professor Lei Zhang, working on the frontiers of computer vision, multimodal foundation models, and generative AI.

“Y learning and beyond — for future visual enhancement and understanding.” — VCLab Mission
● Based in Hung Hom, Kowloon

Rooted at The Hong Kong Polytechnic University.

Our lab sits inside the Department of Computing on PolyU's brick‑red Hung Hom campus — home to Li Ka Shing Tower, the Jockey Club Innovation Tower by Zaha Hadid, and a vibrant community of researchers pushing the boundaries of science and design.

PQ816Lab Office
Hung HomKowloon, HK
Dept. of ComputingThe Hong Kong Polytechnic University
About the Lab

A home for curious visual-intelligence researchers.

Based in the Department of Computing, PolyU, VCLab explores both fundamental and applied problems in visual computing, with strong industrial collaboration and a global publication footprint.

The Visual Computing Lab (VCLab) at The Hong Kong Polytechnic University pursues research across the full stack of modern visual intelligence — from low-level image and video restoration, through multimodal perception and reasoning, to large-scale generative models, 3D reconstruction, new network architectures and rigorous evaluation benchmarks.

Our work is regularly published in top-tier venues including CVPR, ICCV, ECCV, NeurIPS, ICLR, TPAMI and IJCV. Prof. Zhang is also with OPPO Research Institute, supporting active industry-connected research.

We welcome talented students, postdocs and interns who care deeply about visual intelligence. If our mission resonates with you, come join us →

Computer Vision Image / Video Restoration Generative Models MLLM / VLM 3D Vision Efficient Models Benchmarks
LZ
Prof. Lei Zhang
Chair Professor · IEEE Fellow
PolyU OPPO Research Computer Vision
Personal homepage ↗
Google Scholar ↗
Latest News

What's happening at VCLab.

View all news →
2026
12 newly accepted works: 9 CVPR 2026 papers (including 2 Highlights and 1 Oral), 2 ICLR 2026 papers and 1 IJCV article.
Accepted
CVPR 2026
VOSR — a vision-only generative image super-resolution model trained without text–image pairs — is accepted to CVPR 2026.
Accepted
CVPR 2026
Omni-3DEdit, our generalized one-pass 3D editing framework, is accepted as a CVPR 2026 Highlight.
Highlight
Open
Recruiting: multiple PhD, postdoc and research intern positions jointly with OPPO Research Institute. See Join Us.
Hiring
Preprints
VideoVerse & TIIF-Bench are listed as preprints on T2V world-model capability and T2I instruction following.
Preprint
Selected Publications

Recent work from our lab.

A curated selection of recent VCLab publications. For the full list, see Prof. Zhang's publication page ↗.

Our Team

People behind the work.

A close-knit research team passionate about pushing visual intelligence forward.

Faculty
LZ
张磊
Chair Professor
ZN
张宁
Postdoctoral Fellow
ZZ
郑兆晖
Postdoctoral Fellow
HC
何晨杭
Research Assistant Professor
Team Members
Alumni

Our alumni are now at leading universities and companies including MSRA, Huawei Noah's Ark Lab, Meituan, Tencent AI Lab, Alibaba DAMO, OPPO, ByteDance and more.

Open Positions

Join us in shaping
the future of visual intelligence.

We are recruiting PhD students (jointly trained with OPPO Research Institute), postdocs and research interns in areas including image / video restoration and enhancement, image / video generation, LLM / VLM, Mobile MLLM, visual understanding, quality assessment and unified models.

Contact

Get in touch.

Prof. Lei Zhang
Department of Computing
The Hong Kong Polytechnic University
Hung Hom, Kowloon, Hong Kong

Office: PQ816
Email: cslzhang [at] comp.polyu.edu.hk

For general lab inquiries, collaborations and press, please email Prof. Lei Zhang. For prospective students, please include your CV and a brief statement of interest.