Bio
Yakun Ju is currently an Assistant Professor (PhD Supervisor) with the Computing and Mathematical Sciences, University of Leicester, United Kingdom. Prior to this, he served as a Research Fellow in the ROSE Lab at Nanyang Technological University, Singapore, and a Postdoctoral Fellow at The Hong Kong Polytechnic University, Hong Kong SAR. His research interests include 3D reconstruction, medical image processing, and underwater visual perception. He has authored over 70 peer-reviewed publications in leading journals and conferences such as TPAMI, TVCG, TIP, IJCV, and holds multiple patents, with technology transfer applications 480,000 CNY (approximately 70,000 USD). [Official Website]
Education
- Sep 2016 - Jun 2022: Ph.D., School of Computer Science, Ocean University of China, China, Supervised by Prof. Junyu Dong (董军宇).
- Sep 2012 - Jun 2016: B. Eng., School of Mechanical Engineering, Sichuan University, China.
Employment History
- Nov 2024 - Now: Assistant Professor from the School of Computing and Mathematical Sciences, University of Leicester, United Kingdom.
- Sep 2023 - Nov 2024: Research Fellow, ROSE Lab, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, working with Prof. Alex Chichung Kot (SAEng, IEEE Fellow).
- Sep 2022 - Sep 2023: Postdoctoral Fellow, Department of Electrical and Electronic Engineering, Hong Kong Polytechnic University, Hong Kong SAR, working with Prof. Kenneth Kin-Man Lam (IEEE SPS Vice President).
Academic Service
- Associate Editor/Editorial Board: Pattern Recognition (PR), Machine Intelligence Research (MIR), CAAI Transactions on Intelligence Technology (CAAI TRIT), Applied Soft Computing (ASOC), Neurocomputing, Intelligent Marine Technology and Systems (IMTS).
- Guest Editor: Journal of the Optical Society of America A (JOSA A), Ocean Engineering (OE), Pattern Recognition (PR), Computer Vision and Image understanding (CVIU).
- Conference Chair: Publication Chair - BMVC 2026, Program Chair - IDASS2026.
- Workshop Organizer: IEEE ICME 2026 Workshop: P3DMM, IEEE ICME 2025 Workshop: MUIPE.
Selected Publication
Revisiting One-stage Deep Uncalibrated Photometric Stereo via Fourier Embedding
Yakun Ju, Boxin Shi, Bihan Wen, Kin-Man Lam, Xudong Jiang, Alex C. Kot.
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025. [Paper]
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]
Photometric Regularization for 3D Gaussian Splatting in Multi-view Surface Projection
Yakun Ju, Yuying Zhao, Jun Xiao, Cong Zhang, Zheheng Jiang, Huiyu Zhou, Wei Zhou, Hui Yu, Junyu Dong.
IEEE Journal of Selected Topics in Signal Processing (JSTSP), 2025. [Paper]
Estimating High-resolution 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]
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, 2024. [Paper]
FNIN: A Fourier Neural Operator-based Numerical Integration Network for Surface-from-gradients
Jiaqi Leng, Yakun Ju†, Yuanxu Duan, Jiangnan Zhang, Qingxuan Lv, Zuxuan Wu, Hao Fan.
Annual AAAI Conference on Artificial Intelligence (AAAI)*, 2025. [Paper]
Patents
- A Single Frame Image 3D Reconstruction Device and Method Based on Deep Learning, CN107862741, Yakun Ju, Junyu Dong, Lin Qi, Liang Lu, Technology Transfer Applications 480,000 CNY (approximately 70,000 USD)
- High-frequency Region Enhancement Photometric Stereo Method Based on Deep Learning, CN113936117, Yakun Ju, Junyu Dong, Feng Gao
- Multispectral photometric stereo surface normal recovery method based on deep learning, CN110060212, Yakun Ju, Junyu Dong, Lin Qi
- A Transformer-based face image super-resolution method, CN113191953, Muwei Jian, Rui Wang, Xing Wang, Yakun Ju, etc.
- A method for grading diabetic retinopathy based on a three-stage attention network, CN115587979, Muwei Jian, Hongyu Chen, Rui Wang, Yakun Ju, etc.
Awards
- ACM China Council Qingdao Chapter Outstanding Doctoral Dissertation Award, 2022
- Inspur Scholarship, 2021
- National Scholarship for Doctoral Students, 2020
- Goers Acoustic Scholarship, 2017