Zhihong Zhang

I am a research engineer specializing in computational photography and computer vision. My goal is to develop comprehensive sensing-processing-tasking frameworks that enhance the performance of both low-level and high-level vision tasks. This involves the co-design of front-end imaging systems and backend vision algorithms.

I earned my Ph.D. in Control Science and Engineering from Tsinghua University in 2024, under the guidance of Prof. Jinli Suo. Prior to that, I obtained my B.Eng. in Electronics and Information Engineering from Xidian University in 2019.

My current interests include coded aperture/exposure imaging, low-light imaging, high-speed imaging, deblurring, denoising, event cameras, and diffusion models.

Recent News

Jul 28, 2023	Our paper “Deep Coded Exposure: End-to-End Co-optimization of Flutter Shutter and Deblurring Processing for General Motion Blur Removal” is accepted by *Photonics Res.*
Feb 8, 2023	Our paper “INFWIDE: Image and Feature Space Wiener Deconvolution Network for Non-blind Image Deblurring in Low-Light Conditions” is accepted by *IEEE Trans. Image Process.*.
Jan 1, 2023	Our paper “A mutually boosting dual sensor computational camera for high quality dark videography” is accepted by *Information Fusion*.
Sep 22, 2022	Our paper “From compressive sampling to compressive tasking: retrieving semantics in compressed domain with low bandwidth” is accepted by *PhotoniX*.
Sep 22, 2021	Our paper “Ten-Mega-Pixel Snapshot Compressive Imaging with a Hybrid Coded Aperture” is accepted by *Photonics Res.*

Selected Publications

Photonics Res.
Deep Coded Exposure: End-to-End Co-optimization of Flutter Shutter and Deblurring Processing for General Motion Blur Removal

Zhihong Zhang, Kaiming Dong, Jinli Suo*, and Qionghai Dai

Photonics Research, 2023

Abstract Bib HTML Code

We proposed an end-to-end framework to handle general motion blurs with a unified deep neural network, and optimize the shutter’s encoding pattern together with the deblurring processing to achieve high-quality sharp images.
title = {Deep Coded Exposure: End-to-End Co-optimization of Flutter Shutter and Deblurring Processing for General Motion Blur Removal}, author = {Zhang, Zhihong and Dong, Kaiming and Suo*, Jinli and Dai, Qionghai}, journal = {Photonics Research}, year = {2023}, volume = {11}, number = {10}, pages = {1678}, doi = {10.1364/PRJ.489989}, }
IEEE TIP
INFWIDE: Image and Feature Space Wiener Deconvolution Network for Non-blind Image Deblurring in Low-Light Conditions

Zhihong Zhang, Yuxiao Cheng, Jinli Suo*, Liheng Bian, and Qionghai Dai

IEEE Transactions on Image Processing, 2023

Abstract Bib HTML Code

Under low-light environment, handheld photography suffers from severe camera shake under long exposure settings. Sophisticated noise and saturation regions are two dominating challenges in practical low-light deblurring. In this work, we propose a novel non-blind deblurring method dubbed image and feature space Wiener deconvolution network (INFWIDE) to tackle these problems systematically.
@article{infwide_zhihong, title = {{{INFWIDE}}: {{Image}} and Feature Space Wiener Deconvolution Network for Non-blind Image Deblurring in Low-Light Conditions}, author = {Zhang, Zhihong and Cheng, Yuxiao and Suo*, Jinli and Bian, Liheng and Dai, Qionghai}, journal = {IEEE Transactions on Image Processing}, year = {2023}, volume = {32}, pages = {1390--1402}, doi = {10.1109/TIP.2023.3244417}, }

PhotoniX

From Compressive Sampling to Compressive Tasking: Retrieving Semantics in Compressed Domain with Low Bandwidth

Zhihong Zhangᐪ, Bo Zhangᐪ, Xin Yuanᐪ, Siming Zheng, Xiongfei Su, and 3 more authors

PhotoniX, 2022

Abstract Bib HTML

@article{zhang2022CompressiveSampling,
  title = {From Compressive Sampling to Compressive Tasking: Retrieving Semantics in Compressed Domain with Low Bandwidth},
  shorttitle = {From Compressive Sampling to Compressive Tasking},
  author = {Zhangᐪ, Zhihong and Zhangᐪ, Bo and Yuanᐪ, Xin and Zheng, Siming and Su, Xiongfei and Suo*, Jinli and Brady, David J. and Dai*, Qionghai},
  year = {2022},
  journal = {PhotoniX},
  volume = {3},
  number = {1},
  pages = {19},
}

Photonics Asia

Denoising of Event-Based Sensors with Deep Neural Networks

Zhihong Zhang, Jinli Suo*, and Qionghai Dai

In Optoelectron. Imaging Multimed. Technol. VIII, 2021

Abstract Bib HTML Code Poster

@inproceedings{Event_denoise,
  title = {Denoising of Event-Based Sensors with Deep Neural Networks},
  booktitle = {Optoelectron. {{Imaging Multimed}}. {{Technol}}. {{VIII}}},
  author = {Zhang, Zhihong and Suo*, Jinli and Dai, Qionghai},
  year = {2021},
  volume = {11897},
  pages = {203--209},
  publisher = {{SPIE}},
  organization = {{International Society for Optics and Photonics}},
}

Photonics Res.

Ten-Mega-Pixel Snapshot Compressive Imaging with a Hybrid Coded Aperture

Zhihong Zhangᐪ, Chao Dengᐪ, Yang Liu, Xin Yuan, Jinli Suo*, and 1 more author

Photonics Research, 2021

Abstract Bib HTML Code

@article{zhang2021TenmegapixelSnapshot,
  title = {Ten-Mega-Pixel Snapshot Compressive Imaging with a Hybrid Coded Aperture},
  author = {Zhangᐪ, Zhihong and Dengᐪ, Chao and Liu, Yang and Yuan, Xin and Suo*, Jinli and Dai, Qionghai},
  year = {2021},
  journal = {Photonics Research},
  volume = {9},
  number = {11},
  pages = {2277--2287},
}

Academic Service

Reviewer:	IEEE TCSVT , Photonics Res. , Opt. Express , Opt. Letters , JOSA A