Wenhan Luo

Email     Scholar     Publication     Code     Links

I am an applied research scientist at Tencent, where I work on solving real-world problems using computer vision and machine learning techniques. Prior to Tencent, I worked for Amazon (A9) in Palo Alto, California, where I developed deep models for better visual search experience. Before that, I worked as a research scientist in Tencent AI Lab. The techniques I have developed/involved have been shipped to several products in Tencent such as WeChat, Tencent Video, and myapp. I received the Ph.D. degree from Imperial College London, UK, 2016, M.E. degree from Institute of Automation, Chinese Academy of Sciences, China, 2012 and B.E. degree from Huazhong University of Science and Technology, China, 2009. [CV]



Research

I am interested in several topics in computer vision and machine learning. Specifically, my current research focuses on creative AI, such as image/video synthesis.



Updates

2022/01 - TPAMI paper accepted (video deraining).

2021/09 - TIP paper accepted (image deraining).

2021/08 - Invited to serve as a Senior PC member for AAAI 2022.

2021/08 - TIP paper accepted (image desnow).

2021/07 - Paper accepted by ICCV2021 (image SR benchmarking).

2021/07 - One paper (image deblur & SR) to appear in IEEE Transactions on Image Processing.

2021/06 - TMM paper accepted (action recognition).

2021/05 - Our work of active visual tracking is accepted by ICML2021.

2021/05 - One paper of image dehazing to appear in IEEE Transactions on Image Processing.

2021/04 - Our work of human image synthesis is accepted to appear in TPAMI.

2021/03 - One paper to appear in IEEE Transactions on Geoscience and Remote Sensing.

2021/02 - One paper to appear in IEEE Transactions on Multimedia.

2020/12 - The paper "Multiple Object Tracking: A Literature Review" is accepted by Artificial Intelligence.



Recent Projects

Fine-grained Image-to-Image Transformation towards Visual Recognition,
W. Xiong, Y. He, Y. Zhang, W. Luo, L. Ma, J. Luo,
Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), USA, 2020.

Image-to-image translation with fine-grained category towards maintaining identity information.


Liquid Warping GAN: A Unified Framework for Human Motion Imitation, Appearance Transfer and Novel View Synthesis,
W. Liu+, Z. Piao, J. Min, W. Luo, L. Ma, S. Gao,
Proc. of International Conference on Computer Vision (ICCV), Korea, 2019.

A unified framework for human motion transfer, appearance transfer and novel view synthesis using GAN.


End-to-end Active Object Tracking via Reinforcement Learning,
W. Luo*, P. Sun*, F. Zhong, W. Liu, T. Zhang and Y. Wang,
International Conference on Machine Learning (ICML), Sweden, 2018.

The first work proposing the active visual tracking problem and addressing it with reinforcement learning.


Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks,
W. Xiong+, W. Luo, L. Ma, W. Liu and J. Luo,
Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), USA, 2018.

A multi-stage GAN framework to generate time-lapse video given a single image.



I like this website           Design credit