Yakun Ju (舉雅琨)
 |
Lecturer (Assistant Professor) [Google Scholar] [ORCID] [ResearchGate] |
Biography
Yakun Ju is currently the Lecturer (Assistant Professor) at the School of Computing and Mathematical Sciences, University of Leicester. Prior to this, he served as the Research Fellow at the ROSE Lab , School of Electrical and Electronic Engineering, Nanyang Technological University, working with Professor [Alex Chichung Kot]. He also held a Postdoctoral Fellowship at the Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, working with Professor [Kin-Man Lam].
Yakun earned his B.E. from the School of Mechanical Engineering, Sichuan University, in 2016, and his Ph.D. from the School of Computer Science and Technology, Ocean University of China, in 2022, where he was supervised by Professor [Junyu Dong]. During 2020 and 2021, he worked as a Research Assistant at Peking University with Professor [Yuxin Peng] and at The Hong Kong Polytechnic University with Professor [Kin-Man Lam].His research focuses on 3D reconstruction, medical image processing, underwater information perception, computational imaging, and low-level vision tasks. Dr. Ju also reviews for various journals and conferences, serves on editorial board/guest editor for 6 journals, and program chair/committee for 4 conferences.
Academic Service
Associate Editor/Editorial Board: PLOS ONE
Associate Editor/Editorial Board: Frontiers in Artificial Intelligence
Associate Editor/Editorial Board: Intelligent Marine Technology and Systems
Associate Editor/Editorial Board: Metaverse
Guest Editor: Computer Vision and Image understanding-SI:"Advanced Computational Imaging and Photography Measurement"
Guest Editor: Photonics-SI:"Advanced Photometric 3D Reconstruction and beyond"
Conference Program Chair: IDASS 2024
Conference Program Committee: IEEE ICIP 2024 Workshop: AI4IPo Workshop
Session Chair: IEEE ICME 2023
Selected Publications
Deep Learning Methods for Calibrated Photometric Stereo and Beyond
Yakun Ju, Kin-Man Lam, Wuyuan Xie, Huiyu Zhou, Junyu Dong, Boxin Shi
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2024 [Paper]
Normattention-PSN: A High-Frequency Region Enhanced Photometric Stereo Network with Normalized Attention
Yakun Ju, Boxin Shi, Muwei Jian, Lin Qi, Junyu Dong, Kin-Man Lam
International Journal of Computer Vision (IJCV), 2022 [Paper]
Recovering Surface Normal and Arbitrary Images: A Dual Regression Network for Photometric Stereo
Yakun Ju, Junyu Dong, Sheng Chen
IEEE Transactions on Image Processing (TIP), 2021 [Paper]
GR-PSN: Learning to Estimate Surface Normal and Reconstruct Photometric Stereo Images
Yakun Ju, Boxin Shi, Yang Chen, Huiyu Zhou, Junyu Dong, Kin-Man Lam
IEEE Transactions on Visualization and Computer Graphics (TVCG), 2023 [Paper]
Estimating Highresolution Surface Normals via Low-resolution Photometric Stereo Images
Yakun Ju, Muwei Jian, Cong Wang, Cong Zhang, Junyu Dong, Kin-Man Lam
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023 (ESI Highly Cited Paper) [Paper]
Incorporating Lambertian Priors into Surface Normals Measurement
Yakun Ju, Muwei Jian, Shaoxiang Guo, Yingyu Wang, Huiyu Zhou, Junyu Dong
IEEE Transactions on Instrumentation and Measurement (TIM), 2021 [Paper]
Underwater Surface Normal Reconstruction via Cross-grained Photometric Stereo Transformer
Yakun Ju, Ling Li, Xian Zhong, Yuan Rao, Yanru Liu, Junyu Dong, Alex C. Kot
IEEE Journal of Oceanic Engineering (JOE), 2024 [Paper]
Towards Marine Snow Removal with Fusing Fourier Information
Yakun Ju, Jun Xiao, Cong Zhang, Hao Xie, Anwei Luo, Huiyu Zhou, Alex C. Kot
Information Fusion (INFFUS), 2024 [Paper]
Learning Conditional Photometric Stereo with High-resolution Features
Yakun Ju, Yuxin Peng, Muwei Jian, Feng Gao, Junyu Dong
Computational Visual Media (CVMJ), 2022 [Paper]
A dual-cue network for multispectral photometric stereo
Yakun Ju, Xinghui Dong, Yingyu Wang, Lin Qi, Junyu Dong
Pattern Recognition (PR), 2020 [Paper]
Learning Conditional Photometric Stereo with High-resolution Features
Yakun Ju, Kin-Man Lam, Yang Chen, Lin Qi, Junyu Dong
International Conference on International Joint Conferences on Artificial Intelligence (IJCAI), 2020 [Paper]
A deep-shallow and global–local multi-feature fusion network for photometric stereo
Yanru Liu, Yakun Ju*, Muwei Jian, Feng Gao, Yuan Rao, Yeqi Hu, Junyu Dong
Image and Vision Computing (IVC), 2022 [Paper]
A Structure-Affinity Dual Attention-based Network to Segment Spine for Scoliosis Assessment
Hao Xie, Zixun Huang, Frank H.F. Leung, Yakun Ju*, Yong-Ping Zheng, Sai Ho Ling
IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2023 [Paper]
Exposing Image Splicing Traces in Scientific Publications via Uncertainty-guided Refinement
Xun Lin, Wenzhong Tang, Haoran Wang, Yizhong Liu, Yakun Ju, Shuai Wang, Zitong Yu
Patterns - Cell Press, 2024 [Paper]
Learning General Descriptors for Image Matching with Regression Feedback
Yuan Rao, Yakun Ju, Cong Li, Eric Rigall, Jian Yang, Hao Fan, Junyu Dong
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2023 [Paper]
Learning Enriched Feature Descriptor for Image Matching and Visual Measurement
Yuan Rao, Yakun Ju, Sen Wang, Hao Fan, Junyu Dong
IEEE Transactions on Instrumentation and Measurement (TIM), 2023 [Paper]
3D Hand Pose Estimation from Monocular RGB with Feature Interaction Module
Shaoxiang Guo, Eric Rigall, Yakun Ju, Junyu Dong
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022 [Paper]
Efficient Inductive Vision Transformer for Oriented Object Detection in Remote Sensing Imagery
Cong Zhang, Jingran Su, Yakun Ju, Kin-Man Lam, Qi Wang
IEEE Transactions on Geoscience and Remote Sensing (TGRS), 2023 (ESI Highly Cited Paper) [Paper]
Learning General Feature Descriptor for Visual Measurement With Hierarchical View Consistency
Yuan Rao, Jian Yang, Yakun Ju, Cong Li, Eric Rigall, Hao Fan, Junyu Dong
IEEE Transactions on Instrumentation and Measurement (TIM), 2022 [Paper]
Flow-Edge-Net: Video Saliency Detection Based on Optical Flow and Edge-Weighted Balance Loss
Muwei Jian, Xiangwei Lu, Xiaoyang Yu, Yakun Ju, Hui Yu, Kin-Man Lam
IEEE Transactions on Computational Social Systems (TCSS), 2023 [Paper]
pmBQA: Projection-based Blind Point Cloud Quality Assessment via Multimodal Learning
Wuyuan Xie, Kaimin Wang, Yakun Ju, Miaohui Wang
ACM International Conference on Multimedia (MM), 2023 [Paper]
Towards Progressive Multi-Frequency Representation for Image Warping
Jun Xiao, Zihang Lyu, Cong Zhang, Yakun Ju, Changjian Shui, Kin-Man Lam
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024 [Paper]
Promptrestorer: A prompting image restoration method with degradation perception
Cong Wang, Jinshan Pan, Wei Wang, Jiangxin Dong, Mengzhu Wang, Yakun Ju, Junyang Chen
Advances in Neural Information Processing Systems (NeurIPS), 2023 [Paper]
Funds and Projects
3D human face portraits generation with mobile devices, Singapore A*STAR BMRC Strategic Positioning Fund, CI
Advanced AI and image processing techniques for film restoration and movie analysis, Hong Kong Innovation and Technology Commission Fund, CI
Research on key technologies of lightweight dense surface twinning based on normal map, National Natural Science Foundation of China, CI
Research and development of underwater optical high-resolution three-dimensional imager, National Major Scientific Instruments and Equipments Development Project of China, SI
Cooperative research and development of underwater high-precision three-dimensional real-time detection and analysis system, Key Program for International Science and Technology Cooperation Projects of China, SI
Tutorial and Talks
Photometric Stereo: A dense shape recovery method. Online, 29. Oct. 2023: School of Electronic Information and Communications, Huazhong University of Science and Technology
Deep Learning-based Calibrated Photometric Stereo: Review & Future. Beijing, China, 23. Apr. 2023: China3DV 2023
Data-Driven Photometric Stereo. Shenzhen, China, 14. Sept. 2022: School of Computer Science and Software Engineering, Shenzhen University
Data-Driven Photometric Stereo. Qingdao, China, 11. Dec. 2021: CCF China Intelligent Robot Academic Annual Conference 2021
Awards
ACM China Council Qingdao Chapter Outstanding Doctoral Dissertation Award, 2022
National Scholarship for Doctoral Students, 2020
Outstanding Graduates of Shandong Province, 2022
Inspur Scholarship, 2021
Goers Acoustic Scholarship, 2017
Granted Patents
A Single Frame Image 3D Reconstruction Device and Method Based on Deep Learning, CN107862741A, Yakun Ju, Junyu Dong, Lin Qi, Liang Lu
High-frequency Region Enhancement Photometric Stereo Method Based on Deep Learning, CN110060212A, Yakun Ju, Junyu Dong, Feng Gao
Multispectral photometric stereo surface normal recovery method based on deep learning, CN113936117A, Yakun Ju, Junyu Dong, Lin Qi
A Transformer-based face image super-resolution method, CN113191953A, Muwei Jian, Rui Wang, Xing Wang, Yakun Ju, etc.
A method for grading diabetic retinopathy based on a three-stage attention network, CN115587979A, Muwei Jian, Hongyu Chen, Rui Wang, Yakun Ju, etc.
Low-resolution face super-resolution and recognition method based on facial prior knowledge, CN113128467A, Muwei Jian, Rui Wang, Xing Wang, Ji Chen, Yakun Ju, etc.
Mixed facial component recognition method based on non-uniform illumination face image enhancement, CN113239823A, Muwei Jian, Rui Wang, Xing Wang, Chengdong Li, Yakun Ju, etc.