About Me
I am currently a computer vision researcher in Tencent. My current interest includes super-resolution, debanding, style transfer, depth estimation, image inpainting, gaze tracking, object detection, and so on. Moreover, I like to challenge new topics.
Educations
Sun Yat-sen University (SYSU, 中山大学)(opens new window), Guangzhou, China
Sept. 2019 ~ June 2021
M.S. Degree Received in School of Intelligent Systems EngineeringJinan University (JNU, 暨南大学)(opens new window), Guangzhou, China
Sept. 2015 ~ June 2019
B.S. Degree Received in School of Intelligent Systems Science and Engineering
Works & Internships
Tencent (腾讯), Shenzhen, China
July 2021 ~ Present
(Full-time) Computer Vision ResearcherHuawei (华为), Shenzhen, China
July 2018 ~ Oct. 2018
(Intern) Software Development Engineer
Publications
-
Huanrong Zhang, Jie Xiao, Zhi Jin, et al. Multi-scale Image Super-Resolution via A Single Extendable Deep Network. IEEE Journal of Selected Topics in Signal Processing (JSTSP). 2021.
[Paper(opens new window)] [Code(opens new window)] -
Huanrong Zhang, Zhi Jin, Xiaojun Tan, et al. Towards Lighter and Faster: Learning Wavelets Progressively for Image Super-Resolution. Proceedings of the 28th ACM International Conference on Multimedia (ACM MM). 2020.
[Paper(opens new window)] [Code(opens new window)] -
Haoran Qi, Huanrong Zhang, Zhi Jin, et al. SemFSR: An Unsupervised Face SR with Semantic Features for Multiple Degradations. IEEE International Conference on Tools with Artificial Intelligence (ICTAI). 2021.
[Paper(opens new window)] -
Meng Pan, Huanrong Zhang, Jiahao Wu, et al. Self-Distillation Network for Indoor and Outdoor Monocular Depth Estimation. Multimedia Tools and Applications. 2022.
[Paper(opens new window)] -
Yinhe Qi, Huanrong Zhang, Zhi Jin, et al. Depth-guided Asymmetric CycleGAN for Rain Synthesis and Image Deraining. Multimedia Tools and Applications. 2022.
[Paper(opens new window)] -
Hongjun Wu, Haoran Qi, Huanrong Zhang, et al. Reconstruction with Robustness: A Semantic Prior Guided Face Super-Resolution Framework for Multiple Degradations. Image and Vision Computing. 2023.
[Paper(opens new window)] -
Jie Xiao, Zhi Jin, Huanrong Zhang, et al. A General Model Compression Method for Image Restoration Network. Signal Processing: Image Communication. 2021.
[Paper(opens new window)] [Code(opens new window)] [Supp(opens new window)] -
Meng Pan, Huanrong Zhang, Zhi Jin, et al. Pixel Classification-based Monocular Depth Estimation. China Automation Congress (CAC). 2020.
[Paper(opens new window)]
Workshops
-
Lugmayr et al. NTIRE 2021 Learning the Super-Resolution Space Challenge. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2021.
[Paper(opens new window)] -
Zhang et al. NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2020.
[Paper(opens new window)]
Projects
腾讯视频-臻彩视听. In Tencent Video. 2021 ~ Present.
Face and Gaze-based Intelligence Interactivity on Huawei HI3519A Chip. In Sun Yat-sen University. 2019.
State Detection of Fire Door based on Video Frames. In Jinan University. 2018.
Awards
Asia Supercomputer Community (ASC) Student Supercomputer Challenge 2019: First Prize and Application Innovation Award (FaceSR).
CVPR Workshop NTIRE 2021 Learning the Super-Resolution Space Challenge: Finals Award.
CVPR Workshop NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Finals Award.
Jinan University: 1st Prize Scholarship (2016 ~ 2017, 2018 ~ 2019) and 3rd Prize Scholarship (2017 ~ 2018).
Sun Yat-sen University: 3rd Prize Scholarship (2019 ~ 2020, 2020 ~ 2021).
Patents
视频增强方法、装置、设备、存储介质及程序产品(一种基于三维查找表的时域稳定的视频增强方法), 2023, CN117061683A.
一种视频帧异常检测方法、装置、计算机设备和存储介质(一种基于光流的相邻视频帧亮度变化异常的检测方法), 2023, CN116977372A.
IMAGE PROCESSING METHOD, APPARATUS, DEVICE, STORAGE MEDIUM AND COMPUTER PROGRAM PRODUCT (An Adaptive Sharpening Method for the Focus Area of Images or Videos), 2023, HK40079091(Application in force).
图像处理方法、装置、设备、存储介质和计算机程序产品(一种针对图像或视频对焦区域的自适应锐化方法), 2023, CN115619683B(已授权).
TRAINING METHOD OF IMAGE PROCESSING MODEL, VIDEO PROCESSING METHOD, DEVICE AND EQUIPMENT (An Detail Enhancement Method for Videos with Subtitles), 2023, HK40074929(Patent in force, 香港专利已批予).
图像处理模型的训练方法、视频处理方法、装置及设备(一种适用于含字幕视频的清晰度增强方法), 2022, CN115205164B(已授权).
基于增强图像的图像处理方法、装置和计算机设备(一种基于局部融合的增强后处理方法), 2022, CN115115554B(已授权).
一种基于语义特征的人脸超分辨率重建方法及系统, 2022, CN114820310A.
一种合成高仿真图像的方法, 2021, CN113160101B(已授权).
基于图像的消防门及其开关状态的检测方法, 2018, CN109035278B(已授权).
Foundations
国家自然科学基金委员会面上项目, 6207010648, 复杂天气及光照下的移动视觉感知增强理论与方法, 2020, 参与.
Others
Megapixel Image Viewer APP. In Jinan University. 2019.