Special Session 3  会议特别专题 3

Underwater Vision Processing

Description: Approximately 71% of the Earth's surface is covered by water, and the absorption, scattering, and attenuation of light in aquatic environments pose significant challenges to underwater vision tasks. Current challenges include unclear imaging of underwater vision, difficulties of target detection and tracking, and inaccuracies of light-field reconstruction and depth estimation. However, with remarkable advancements in artificial intelligence, modern vision technologies—machine learning and deep learning—offer innovative solutions to these above problems. Research on underwater image processing is crucial for developing key technologies in maritime power strategies. This special issue, titled "Underwater Vision Processing", summarizes recently key technologies and their applications, covering underwater image restoration and enhancement, underwater image quality assessment, underwater object detection and tracking, underwater image depth estimation, underwater light-field reconstruction, underwater 3D scene reconstruction, underwater imaging and compression, and related methods on enhancing other harsh environments (such as haze, dust, and low-light, etc.).

Session organizers
Assoc. Prof. Peixian Zhuang, University of Science and Technology Beijing, China
Assoc. Prof. Weidong Zhang, Henan Institute of Science and Technology, China
Dr. Zhenqi Fu, Tsinghua University, China
Dr. Jieyu Yuan, Nankai University, China
Dr. Zheng Liang, Anhui University, China

The topics of interest include, but are not limited to:
▪ Underwater Image Restoration and Enhancement
▪ Underwater Image Quality Evaluation
▪ Underwater Object Detection and Tracking
▪ Underwater Image Depth Estimation
▪ Underwater Light-Field Image Reconstruction
▪ Underwater 3D Scene Reconstruction
▪ Underwater Imaging and Compression
▪ Image enhancement in harsh environment (haze, dust, and low-light, etc.)

Submission method
Submit your Full Paper (no less than 4 pages with two colums) or your paper abstract-without publication (200-400 words) via Online Submission System, then choose Special Session 3 (Underwater Vision Processing)
Template Download

Introduction of Session organizers

Assoc. Prof. Peixian Zhuang, University of Science and Technology Beijing, China

Peixian Zhuang received the Ph.D. degree from Xiamen University in 2016. From 2020 to 2022, He was a Postdoctoral Researcher in Tsinghua University. He is currently an Associate Professor at University of Science and Technology Beijing. He is an IEEE Senior Member, and his research interests involve underwater image processing, and artificial intelligence. He has published more than 60 papers (10 ESI Highly Cited and 6 ESI Hot Papers) in top-tier international journals and conferences, including IEEE TIP, TCSVT, TCYB, TGRS, TMM, with over 3700 Google citations. He also has authored 1 English book and 10 Chinese invention patents. In recent years, he has presided over a number of underwater vision processing projects, including National Natural Science Foundation of China, China Postdoctoral Science Foundation, and has participated in National Key Research and Development Program of China. He was entitled "Young Scientist for Marine Power Nation", ScholarGPS "World's Top 0.05% Scholars", "World's Top 2% Scientists", "IFAC EAAI Best Paper Award", and "Outstanding Doctoral Dissertation in Fujian Province". Besides, he has served as Regional Chair of ICIGP and Session Chair of IEEE ICSIP, Youth Editorial Board Members of multiple journals, Guest Editor of the Journal of Image & Graphics, Guest Editor of the Journal of Electronics & Information Technology, etc.



Assoc. Prof. Weidong Zhang, Henan Institute of Science and Technology, China

Weidong Zhang received the Ph.D. degree from the Dalian Maritime University in 2022. From 2022 to 2024, he is a Lecturer the School of Information Engineering at Henan Institute of Science and Technology. From 2024 to now, he is an Associate Professor the School of Information Engineering at Henan Institute of Science and Technology, and he is also a Postdoctoral Fellow at Zhengzhou University. His main research interests include underwater image processing and understanding, remote sensing image interpretation and analysis, and visual content enhancement in an open environment, etc. He has published more than 70 peer-reviewed papers in prestigious international journals and conferences (such as IEEE TIP, TMM, TGRS, TCSVT, AAAI), and he also has been served as a Program Committee member for AAAI-2024, AAAI-2025, and ICIGP-2025, and a youth editorial board member of the Journal of Naval Aviation University.



Dr. Zhenqi Fu, Tsinghua University, China

Zhenqi Fu received the Ph.D. degree in Signal and Information Processing from Xiamen University, Xiamen, China, in 2023. From 2021 to 2022, he was a Visiting Ph.D. Student at the School of Electrical & Electronic Engineering, Nanyang Technological University, Singapore. He is currently a postdoctoral researcher in the Department of Automation, Tsinghua University, Beijing, China. He has published over 20 peer-reviewed SCI/EI-indexed papers and has served as a reviewer for top-tier journals and conferences, including IEEE TPAMI, IEEE TIP, IJCV, ICLR, ICML, NeurIPS, CVPR, ICCV, ECCV, etc. His current research interests include Low-level Vision, Biomedical Imaging, and Deep Learning.



Dr. Jieyu Yuan, Nankai University, China

Jieyu Yuan received the Ph.D. degree in Computer Technology and Application from School of Computer Science and Engineering, Macau University of Science and Technology, Taipa, Macau, China, in 2024. He is currently a postdoctoral researcher with the VCIP, College of Computer Science, Nankai University, Tianjin, China. He has published over 10 peer-reviewed papers in SCI(E)-indexed journals. He has serves as a reviewer for top-tier journals, including TIP, IJCV, TMM, TCSVT, TGRS, TIM, EAAI and JOE, and was one of the Outstanding Reviewers of 2024 in JOE. His research interests include Computer Vision, 3D Vision, and Artificial Intelligence.



Dr. Zheng Liang, Anhui University, China

 Zheng Liang received the Ph.D. degree in Computer Applied Technology from the School of Information Science and Technology, Dalian Maritime University, Dalian, China, in 2021. Now, he is a Lecturer with the School of Internet, Anhui University, Hefei, China. He has published over 20 peer-reviewed SCI/EI-indexed papers, and has served as a reviewer for top-tier journals and conferences, including IEEE TCSVT, IEEE TII, IEEE TCE, IEEE TIM, OLT, OLE, AAAI, etc. His research interests include Image Restoration, Object Detection, and Deep Learning.