Iksung Kang
{first name}.{last name} at alum.mit.edu

I am a computational optical imaging engineer and a recent PhD from MIT EECS. I am currently working as a postdoctoral fellow at UC Berkeley.

At MIT, I was advised by George Barbastathis in 3D Optical Systems Group and worked on (1) robust phase retrieval under low-photon conditions using machine learning and random phase modulation, (2) wavefront aberration estimation for high-contrast imaging of exoplanets, and (3) non-invasive three-dimensional reconstruction of integrated circuits from X-ray ptycho-tomography and ptycho-laminography for rapid semiconductor manufacturing inspection process. I was a recipient of Korea Foundation for Advanced Studies scholarship throughout my doctoral study.

Email  /  Google Scholar

profile photo
Research

My research interests are physics-informed machine learning in computational optical imaging applications. A large part of my research involves incorporating domain knowledge from optical physics into machine learning algorithms.

Journal Publications

Coordinate-based neural representations for computational adaptive optics in widefield microscopy
Iksung Kang, Qinrong Zhang, Stella X. Yu, Na Ji
arXiv, 2307.03812 (2023) (in revision)
Accelerated deep self-supervised ptycho-laminography for three-dimensional nanoscale imaging of integrated circuits
Iksung Kang, Yi Jiang, Mirko Holler, Manuel Guizar-Sicairos, A. F. J. Levi, Jeffrey Klug, Stefan Vogt, George Barbastathis
Optica, 10(8), pp. 1000-1008 (2023)
Attentional Ptycho-Tomography (APT) for three-dimensional nanoscale X-ray imaging with minimal data acquisition and computation time
Iksung Kang, Ziling Wu, Yi Jiang, Yudong Yao, Junjing Deng, Jeffrey Klug, Stefan Vogt, George Barbastathis
Light: Science and Applications, 12(131) (2023)
News: EurekAlert!
Three-dimensional nanoscale reduced-angle ptycho-tomographic imaging with deep learning (RAPID)
Ziling Wu, Iksung Kang, Yudong Yao, Yi Jiang, Junjing Deng, Jeffrey Klug, Stefan Vogt, George Barbastathis
eLight, 3(7) (2023)
Simultaneous spectral recovery and CMOS micro-LED holography with an untrained deep neural network
Iksung Kang, Marc de Cea, Jin Xue, Zheng Li, George Barbastathis, Rajeev J. Ram
Optica, 9(10) (2022)
Dynamical machine learning volumetric reconstruction of objects’ interiors from limited angular views
Iksung Kang, Alexandre Goy, George Barbastathis
Light: Science and Applications, 10(74) (2021)
News: EurekAlert!
Recurrent neural network reveals transparent objects through scattering media
Iksung Kang, Subeen Pang, Qihang Zhang, Nicholas Fang, George Barbastathis
Optics Express, 29(4), pp. 5316-5326 (2020)
Deep residual learning for low-order wavefront sensing in high-contrast imaging systems
Gregory Allan*, Iksung Kang*, Ewan Douglas, George Barbastathis, Kerri Cahoy
Optics Express, 28(18), pp. 26267-26283 (2020) (*: equal contribution)
On the interplay between physical and content priors in deep learning for computational imaging
Mo Deng, Shuai Li, Zhengyun Zhang, Iksung Kang, Nicholas Fang, George Barbastathis
Optics Express, 28(16), pp. 24152-24170 (2020)
Phase Extraction Neural Network (PhENN) with Coherent Modulation Imaging (CMI) for phase retrieval at low photon counts
Iksung Kang, Fucai Zhang, George Barbastathis
Optics Express, 28(15), pp. 21578-21600 (2020)
Learning to synthesize: Robust phase retrieval at low photon counts
Mo Deng, Shuai Li, Alexandre Goy, Iksung Kang, George Barbastathis
Light: Science and Applications, 9(36) (2020)

Conference Proceedings

Deep self-supervised learning for computational adaptive optics in widefield microscopy
Iksung Kang, Qinrong Zhang, Na Ji
Proceedings of SPIE 12388, Adaptive Optics and Wavefront Control for Biological Systems IX, 123880H (16 March 2023)
On the use of deep learning for three-dimensional computational imaging
George Barbastathis, Subeen Pang, Iksung Kang, Ziling Wu, Zhiguang Liu, Zhen Guo, Fucai Zhang
Proceedings of SPIE 12445, Practical Holography XXXVII: Displays, Materials, and Applications, 124450J (8 March 2023)
Three-dimensional reconstruction of integrated circuits by single-angle X-ray ptychography with machine learning
Iksung Kang, Yudong Yao, Junjing Deng, Jeffrey Klug, Stefan Vogt, Steven Honig, George Barbastathis
Imaging and Applied Optics Congress, OSA Technical Digest (Optical Society of America 2021), paper CTu6A.4
Probability of error as an image metric for the assessment of tomographic reconstruction of dense-layered binary-phase objects
Iksung Kang, George Barbastathis
Proceedings of SPIE 11653, Quantitative Phase Imaging VII, 116530T (5 March 2021)
Deep neural networks to improve the dynamic range of Zernike phase-contrast wavefront sensing in high-contrast imaging systems
Gregory Allan*, Iksung Kang*, Ewan Douglas, Mamadou N'Diaye, George Barbastathis, Kerri Cahoy
Proceedings of SPIE 11443, Space Telescopes and Instrumentation 2020: Optical, Infrared, and Millimeter Wave, 1144349 (13 December 2020) (*: equal contribution)
A portable, low-cost, 3D-printed main magnetic field system for magnetic imaging
Iksung Kang
2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2017, pp. 3533-3536

Technical Reports

LION: Learning to Invert 3D Objects by Neural Networks
George Barbastathis, Jungki Song, Ziling Wu, Iksung Kang, Subeen Pang, Zhen Guo
Microsystems Annual Research Report (2021)
Imaging Transparent Objects through Dynamic Scattering Media Using Recurrent Neural Networks
Iksung Kang, Subeen Pang, Qihang Zhang, Nicholas Fang, George Barbastathis
Microsystems Annual Research Report (2021)
On the Use of Deep Learning for Retrieving Phase from Noisy Inputs in the Coherent Modulation Imaging Scheme
Iksung Kang, Fucai Zhang, George Barbastathis
Microsystems Annual Research Report (2020)
Teaching

Each classroom should promote an inclusive learning environment that embraces and respects diverse backgrounds of students as well as providing them with equitable opportunities to learn and practice.

Kaufman Teaching Certificate Program (KTCP), Teaching & Learning Laboratory, Massachusetts Institute of Technology (2021)
I completed seven workshops to develop teaching skills as part of the teaching certificate program. A major part of the program involved introducing students to relevant research in teaching and learning and laying out future teaching models. I also presented two microteaching sessions that were videotaped, where I received feedback on my performance regarding my teaching and provided feedback to other participants.
Teaching Assistant (2.16/2.168 Learning Machines), Department of Mechanical Engieering, Massachusetts Institute of Technology (2020)
I mentored course research projects, contributed to curriculum design, conducted after-hour office hours, and graded assignments. Class taught totaled around 40 students and comprised course research projects on the connection between machine learning and physical systems.
Mentoring

One's education finally becomes meaningful when they share their experiences with others who need them.

End-term Project Mentor, Department of Mechanical Engieering, Massachusetts Institute of Technology (2021)
I mentored a graduate student group in 2.C01/2.C51 Physical Systems Modeling and Design Using Machine Learning course for their end-term project on the image segmentation of noisy ultrasonic images.
End-term Project Mentor, Department of Mechanical Engieering, Massachusetts Institute of Technology (2020)
I mentored two graduate student groups in 2.16/2.168 Learning Machines course for their end-term projects on the reaction modeling to facilitate pharmaceutical process development using machine learning & the control of autonomous ocean vehicles using reinforcement learning.
Volunteer, Korea Foundation for Advanced Studies Overseas Program (2018)
I participated as a volunteer in the Kingdom of Cambodia for a week, teaching children math and building houses.

My website uses this template.