Hengyuan Zhao

Hengyuan Zhao (赵恒远)

From 2022/01, Hengyuan will be a Ph.D. student at NUS' Show Lab, where he will be supervised by Prof. Mike Shou. He formerly worked as a research intern at VIS Baidu Inc. and SenseTime Inc., where he concentrated on image restoration techniques including as super-resolution, denoising, deblurring, and colorization to restore old videos and images. At the same time, he was working as a research assistant supervised by Prof. Chao Dong and Prof. Yu Qiao at the XPixel Group at Shenzhen Institutes of Advanced Technology (SIAT).

Links: Email / GitHub / Google Scholar

Experience

06/2021-10/2021: As a research intern, I joined SenseTime Inc.'s MIG and worked with Fan Zhang.

12/2020-06/2021: As a research intern, I joined Baidu Inc.'s Vision Technology (VIS) and worked with Wenhao Wu.

09/2019-Present: I am a research assistant at SIAT and supervised by Prof. Chao Dong and Yu Qiao.

09/2016-06/2020: I was a undergraduate student at Nanjing University of Posts and Telecommunications, Nanjing, China.

News

[11/2021] Congratulation!!! I will take part in Show Lab in the January of 2022.
[06/2021] Join SenseTime, work with Fan Zhang.
[03/2021] One paper accepted by CVPR, 2021.
[12/2020] Join VIS, Baidu, worked with Wenhao WU.
[08/2020] One paper accepted by ECCV Workshops, 2020.
[05/2020] Participate the Efficient Super-Resoluton Challenge of AIM 2020 (ECCV Workshops). We got fourth place and lowest parameters.
[09/2019] Join MMLAB at SIAT, supervised by Yu Qiao and Chao Dong.
[08/2019] One paper accepted by ICCV Workshops, 2019.

Publications

Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning

Yihao Liu* Hengyuan Zhao* Kelvin C.K. Chan, Xintao Wang, Chen Change Loy, Yu Qiao, Chao Dong.

Under review.

Paper(arxiv) | Codes | BibTex

	Color2Embed: Fast Exemplar-Based Image Colorization using Color Embeddings Hengyuan Zhao, Wenhao Wu, Yihao Liu, Dongliang He. Arxiv.* Paper(arxiv) \| Codes \| BibTex
	ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic Xiangtao Kong, Hengyuan Zhao, Yu Qiao, Chao Dong Computer Vision and Pattern Recognition (CVPR 2021) Paper(arxiv) \| Codes \| BibTex
	Efficient Image Super-Resolution Using Pixel Attention Hengyuan Zhao, Xiangtao Kong, Jingwen He, Yu Qiao, Chao Dong European Conference on Computer Vision Workshops (ECCVW 2020) We got fourth place of Efficient Image Super Resolution Challenge in total 150 participants. (The lowest paramters, 272K) Paper(arxiv) \| Codes \| BibTex
	A Simple and Robust Deep Convolutional Approach to Blind Image Denoising Hengyuan Zhao, Wenze Shao, Bingkun Bao, Haibo Li International Conference on Computer Vision Workshops (ICCVW 2019) Paper \| Codes \| BibTex
	Very Lightweight Photo Retouching Network with Conditional Sequential Modulation Yihao Liu, Jingwen He, Xiangyu Chen, Zhengwen Zhang, Hengyuan Zhao, Chao Dong, Yu Qiao Paper(arxiv) \| Codes \| BibTex

	Color2Embed: Fast Exemplar-Based Image Colorization using Color Embeddings Hengyuan Zhao, Wenhao Wu, Yihao Liu, Dongliang He. Arxiv.* Paper(arxiv) \| Codes \| BibTex
	ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic Xiangtao Kong, Hengyuan Zhao, Yu Qiao, Chao Dong Computer Vision and Pattern Recognition (CVPR 2021) Paper(arxiv) \| Codes \| BibTex
	Efficient Image Super-Resolution Using Pixel Attention Hengyuan Zhao, Xiangtao Kong, Jingwen He, Yu Qiao, Chao Dong European Conference on Computer Vision Workshops (ECCVW 2020) We got fourth place of Efficient Image Super Resolution Challenge in total 150 participants. (The lowest paramters, 272K) Paper(arxiv) \| Codes \| BibTex
	A Simple and Robust Deep Convolutional Approach to Blind Image Denoising Hengyuan Zhao, Wenze Shao, Bingkun Bao, Haibo Li International Conference on Computer Vision Workshops (ICCVW 2019) Paper \| Codes \| BibTex
	Very Lightweight Photo Retouching Network with Conditional Sequential Modulation Yihao Liu, Jingwen He, Xiangyu Chen, Zhengwen Zhang, Hengyuan Zhao, Chao Dong, Yu Qiao Paper(arxiv) \| Codes \| BibTex

Hengyuan Zhao (赵恒远)

Experience

News

Publications

Please contact me if you have any questions about my research.