top of page

Publications

Authorship and contributorship: The asterisks (*) indicate equal contributions. The daggers (†) indicate the (co-)corresponding authorship of the PI. Except for very special cases, mentees hold the (co-)first authorship. The last author position is reserved for the individual who may have given significant intellectual inputs and/or supervised the overall work.

gscholar.png

Diffusion models for three-dimensional (3D) volume reconstruction

Diffusion models can generate high-quality and diverse samples. By changing additional information so-called condition and conditional approach, one can manipulate generation outcomes. The paper proposes a new conditional diffusion model that reconstructs high-quality 3D volumes from a few 2D images with a new vision transformer architecture.

Fast and convergent iterative neural network

Iterative neural networks (INN) are rapidly gaining attention for solving inverse problems in imaging, image processing, and computer vision. The paper proposes the first fast and convergent INN architecture, Momentum-Net.

Autonomous driving using self-supervised imitation learning

End-to-end driving (E2E) is an emerging regression AI technology directly mapping raw vision data on one end to vehicle control signals (e.g., steering angle and throttle) on the other, and is a scalable framework for self-driving cars in new areas. The paper uses the self-supervised imitation learning framework for safe E2E driving in areas where ground-truth vehicle control prediction samples are unavailable.

Light-field imaging using focal stack

Using transparent focal stacks and sophisticated data science solutions, the paper discusses a high-quality three-dimensional (3D) camera that can accurately determine an object’s distance from the lens. The information produced by the 3D camera is critical in biological imaging, autonomous driving, facial recognition and virtual reality. In biological imaging, for example, it is important for researchers to see 3D volume; in autonomous driving, determining an object’s distance is crucial to safety.

Submitted papers

[6] U Jin Jeong, Sumin Roh(†), and Il Yong Chun(†),

"LaB-CL: Localized and Balanced Contrastive Learning for improving parking slot detection,"

submitted to IEEE International Conference on Robotics and Automation (ICRA), Sep. 2024.

[5] Yun Su Jeong(*), Jinkyu Lee(*), and Il Yong Chun,

"DX2CT: Diffusion model for 3D CT reconstruction from bi or mono-planar 2D X-ray(s)",

submitted to IEEE Intl. Conf. on Acoust., Speech, and Signal Process. (ICASSP), Sep. 2024. arXiv:2409.08850

[4] Jin Bok Park(*), Jinkyu Lee(*), Muhyun Back, Hyunmin Han, David T. Ma, Sang Min Won(†), Sung Soo Hwang(†), and Il Yong Chun(†),

“End-to-end driving via self-supervised imitation learning using camera and LiDAR data,”

submitted to Adv. Intell. Syst., Aug. 2023. arXiv:2308.14329.

[3] Il Yong Chun(*,†), Dongwon Park(*), Xuehang Zheng(*), Se Young Chun(†), and Yong Long(†),

“Self-supervised regression learning using domain knowledge: Applications to improving self-supervised denoising in imaging,”

submitted to IEEE Trans. Image Process., May 2022.
[2] Md Yousuf Harun, Thomas T. F. Huang, Joshua Mellinger, Willy Chang, Adrianna Saymo, Brienne Walker, Kristen Hori, M Arifur Rahman, Il Yong Chun(†), and Aaron T. Ohta(†),
“Improved U-Net architecture for human embryo image segmentation,”
submitted to IEEE Trans. Med. Imag., Aug. 2020.
[1] Xuehang Zheng(*), Il Yong Chun(*), Zhipeng Li, Yong Long
, and Jeffrey A. Fessler,
“Sparse-view X-ray CT reconstruction using l1 prior with learned transform,”
submitted to IEEE Trans. Comput. Imag., Feb. 2019.

Submitted

Journal papers

[17] Hye Bin Yoo(*), Hyun Min Han(*), Sung Soo Hwang(†), Il Yong Chun(†),

“Improving neural radiance fields using near-surface sampling with point cloud generation,”

Neural Process. Lett., 56:214:1–22, Jul. 2024.

[16] Hyekyoung Hwang, Il Yong Chun(†), and Jitae Shin(†),

“Improved test input prioritization using verification monitors with false prediction cluster centroids,” 

Electronics Special Issue: Image/Video Processing and Encoding for Contemporary Applications, 13(1):21:1–12, Dec. 2023.

[15] Il Yong Chun(†), Zhengyu Huang(*), Hongki Lim(*), and Jeffrey A. Fessler,

“Momentum-Net: Fast and convergent iterative neural network for inverse problems,” 

IEEE Trans. Pattern Anal. Mach. Intell., 45(5):4915–4931, Apr. 2023.

[14] Zhipeng Li, Yong Long(†), and Il Yong Chun(†),

“An improved iterative neural network for high-quality image-domain material decomposition in dual-energy CT,”

Med. Phys., 50(4):2195–2211, Apr. 2023.

[13] Jinkyu Lee, Muhyun Back, Sung Soo Hwang(†), and Il Yong Chun(†),

“Improved real-time monocular SLAM using semantic segmentation on selective frames,”
IEEE Trans. Intell. Transp. Syst., 24(3):2800–2813, Mar. 2023.

[12] Dehui Zhang(*), Zhen Xu(*), Zhengyu Huang(*), Audrey Rose Gutierrez, Cameron J. Blocker, Che-Hung Liu, Miao-Bin Lien, Gong Cheng, Zhe Liu, Il Yong Chun(†), Jeffrey A. Fessler, Zhaohui Zhong, and Theodore B. Norris,
“3D imaging and tracking with a neural network enabled graphene transparent multi-focal-plane imaging system,”
Nature Commun., 12:2413:1–7, Apr. 2021.
[11] Hongki Lim, Il Yong Chun, Yuni K. Dewaraja, and Jeffrey A. Fessler,
“Improved low-count quantitative PET reconstruction with an iterative neural network,”
IEEE Trans. Med. Imag., 39(11): 3512–3522, Nov. 2020. 
[10] Miao-Bin Lien, Che-Hung Liu, Il Yong Chun, Saiprasad Ravishankar, Hung Nien, Minmin Zhou, Jeffrey A. Fessler, Theodore B. Norris, and Zhaohui Zhong,
“Ranging and light field imaging with transparent photodetectors,”
Nature Photonics, 14(3):143–148, Mar. 2020. [GitHub repo]
[9] Il Yong Chun(†) and Jeffrey A. Fessler,
“Convolutional analysis operator learning: Acceleration and convergence,”
IEEE Trans. Image Process., 29(1): 2108–2122, 2020. [GitHub repo: CONVOLT]
[8] Il Yong Chun(†) and Ben Adcock,
“Uniform recovery from subgaussian multi-sensor measurements,”
Appl. Comput. Harmon. Anal., 48(2): 731–765, Mar. 2020.
[7] Il Yong Chun(*,), David Hong(*), Ben Adcock, and Jeffrey A. Fessler,
“Convolutional analysis operator learning: Dependence on training data,”
IEEE Signal Process. Lett., 26(8):1137–1141, Aug. 2019. [GitHub repo: CONVOLT]
[6] Ikbeom Jang, Il Yong Chun, Sumra Bari, Evan L. Breedlove, Brian R. Cummiskey, Taylor A. Lee, Roy J. Lycke, Victoria N. Poole, Trey E. Shenk, Diana O. Svaldi, Gregory G. Tamer, Jr., Larry J. Leverenz, Eric A. Nauman, and Thomas M. Talavage,
“Every hit matters: White matter integrity changes in high school football athletes are correlated with repetitive head acceleration event exposure,”
Neuroimage: Clinical, 24: 101930, Jul. 2019.
[5] Il Yong Chun() and Jeffrey A. Fessler,
“Convolutional dictionary learning: Acceleration and convergence,”
IEEE Trans. Image Process., 27(4):1697–1712, Apr. 2018. [GitHub repo: CONVOLT]
[4] Il Yong Chun() and Ben Adcock,
“Compressed sensing and parallel acquisition,”
IEEE Trans. Inf. Theory, 63(8):4860–4882, May 2017. 
[3] Il Yong Chun(
), Song Noh, David J. Love, Thomas M. Talavage, Stephen Beckley, and Sherman J. Kisner,
“Mean squared error (MSE)-based excitation pattern design for parallel transmit and receive SENSE MRI image reconstruction,”
IEEE Trans. Comput. Imag., 2(4):424–439, Dec. 2016.
[2] Il Yong Chun(
), Ben Adcock, and Thomas M. Talavage,
“Efficient compressed sensing SENSE pMRI reconstruction with joint sparsity promotion,”
IEEE Trans. Med. Imag., 5(1):354–368, Jan. 2016.
[1] Il Yong Chun(
), Xianglun Mao, Eric L. Breedlove, Larry J. Leverenz, Eric A. Nauman, and Thomas M. Talavage,
“DTI detection of longitudinal WM abnormalities due to accumulated head impacts,”
Dev. Neuropsychol., 40(2):92–97, May 2015.

Journal
Premier conf.

Premier-conference papers

[1] Il Yong Chun(*), Xuehang Zheng(*), Yong Long, and Jeffrey A. Fessler,
“BCD-Net for low-dose CT reconstruction: Acceleration, convergence, and generalization,”
in Proc. Med. Image Compt. and Computer Assist. Interven. (MICCAI), pp. 31-40, Shenzhen, China, Oct. 2019.

Conf.

Conference papers & abstracts

[33] ​​Hyung Sup Yun and Il Yong Chun, "Improving light field reconstruction from limited focal stack using diffusion models," to appear in Proc. IEEE Intl. Workshop on Machine Learning and for Signal Processing (MLSP), Longdon, UK, Sep. 2024. 

[32] Hyun Min Han, Il Yong Chun, Sung Soo Hwang,
“Improvement of NeRF (Neural Radiance Field) using depth information,”
in Proc. Inst. Elect. & Info. Eng. (IEIE) Conf. (Fall), 44(2):329–332, Nov. 2021.
[31] Muhyun Back, Jinkyu Lee, Kyuho Bae, Sung Soo Hwang(†), Il Yong Chun(†),
“Improved and efficient inter-vehicle distance estimation using road gradients of ego and target vehicles,”
in Proc. IEEE Intl. Conf. Auton. Sys. (ICAS), Virtual Conf., Aug. 2021.
[30] Siqi Ye, Yong Long(†), and Il Yong Chun(†),
“Momentum-Net for low-dose CT image reconstruction,”
in Proc. Asilomar Conf. on Signals, Syst., and Comput., Nov. 2020.
[29] Zhengyu Huang, Jeffrey A. Fessler, Theodore B. Norris, Il Yong Chun,
“Light-field reconstruction and depth estimation from focal stack images using convolutional neural networks,”
in Proc. IEEE Intl. Conf. on Acoust., Speech, and Signal Process. (ICASSP), pp. 8648–8652, Barcelona, Spain, May 2020. (Invited paper)
[28] Zhipeng Li, Il Yong Chun, and Yong Long,
“Image-domain material decomposition using an iterative neural network for dual-energy CT,”
in Proc. IEEE Intl. Symp. Biomed. Imag. (ISBI), pp. 651–655, Iowa City, IA, Apr. 2020.
[27] Caroline Crockett, David Hong, Il Yong Chun, and Jeffrey A. Fessler,
“Incorporating handcrafted filters in convolutional analysis operator learning for ill-posed inverse problems,”
in Proc. IEEE Intl. Workshop on Compt. Adv. in Multi-Sensor Adaptive Process. (CAMSAP), pp. 316–320, Guadeloupe, West Indies, Dec. 2019. [GitHub repo: CAOL for Julia(Invited paper)
[26] Hongki Lim, Il Yong Chun, Jeffrey A. Fessler, and Yuni K. Dewaraja,
“Improved low count quantitative SPECT reconstruction with a trained deep learning based regularizer,”
J. Nuc. Med. (Abs. Book), 60(s1):42, May 2019.
[25] Dehui Zhang, Zhen Xu, Zhengyu Huang, Audrey Rose Gutierrez, Il Yong Chun, Cameron J. Blocker, Gong Cheng, Zhe Liu, Jeffrey A. Fessler, Zhaohui Zhong, and Theodore B. Norris,
“Graphene-based transparent photodetector array for multiplane imaging,”
in Proc. Conf. on Lasers and Electro-Optics (CLEO), p. SM4J.2, San Jose, CA, May 2019.
[24] Il Yong Chun(†), Hongki Lim(*), Zhengyu Huang(*), and Jeffrey A. Fessler,
“Fast and convergent iterative signal recovery using trained convolutional neural networks,”
in Proc. Annual Allerton Conf. on Commun., Control, and Comput., pp. 155–159, Monticello, IL, Oct. 2018. (Invited paper)
[23] Il Yong Chun(†) and Jeffrey A. Fessler,
“Convolutional analysis operator learning: Application to sparse-view CT,”
in Proc. Asilomar Conf. on Signals, Syst., and Comput., pp. 1631–1635, Pacific Grove, CA, Oct. 2018. (Invited paper)
[22] Hongki Lim, Jeffrey A. Fessler, Yuni K. Dewaraja, and Il Yong Chun,
“Application of trained deep BCD-Net to iterative low-count PET image reconstruction,”
in Proc. IEEE Nuclear Science Symposium and Medical Imaging Conf. (NSS-MIC), pp. 1–4, Sydney, Australia, Nov., 2018.
[21] Il Yong Chun(†) and Jeffrey A. Fessler,
“Deep BCD-Net using identical encoding-decoding CNN structures for iterative image recovery,”
in Proc. IEEE Image, Video, and Multidim. Signal Process. (IVMSP) Workshop, pp. 1–5, Zagori, Greece, Apr. 2018. 
[20] Cameron J. Blocker*, Il Yong Chun*, and Jeffrey A. Fessler,
“Low-rank plus sparse tensor models for light-field reconstruction from focal stack data,”
in Proc. IEEE Image, Video, and Multidim. Signal Process. (IVMSP) Workshop, pp. 1–5, Zagori, Greece, Apr. 2018.
[19] Saiprasad Ravishankar, Il Yong Chun, and Jeffrey A. Fessler,
“Physics-driven deep training of dictionary-based algorithms for MR image reconstruction,”
in Proc. Asilomar Conf. on Signals, Syst., and Comput., pp. 1859–1863, Pacific Grove, CA, Nov. 2017. (Invited paper)
[18] Il Yong Chun(†) and Jeffrey A. Fessler,
“Convergent Convolutional Dictionary Learning using Adaptive Contrast Enhancement (CDL-ACE): Application of CDL to image denoising,”
in Proc. Sampling Theory and Appl. (SampTA), pp. 460–464, Tallinn, Estonia, Jul. 2017. [GitHub repo: CONVOLT]
[17] Il Yong Chun(†), Xuehang Zheng, Yong Long, and Jeffrey A. Fessler,
“Sparse-view X-ray CT recon- struction using l1 regularization with learned sparsifying transform,”
in Proc. Intl. Mtg. on Fully 3D Image Recon. in Rad. and Nuc. Med. (Fully 3D), pp. 115–119, Xi’an, China, Jun. 2017.
[16] Ikbeom Jang, Il Yong Chun, Sumra Bari, Yukai Zou, Eric A. Nauman, and Thomas M. Talavage,
“DTI reveals persistent effects on white matter in football players with history of sports-related concussion,”
IN Neuroimaging Symp., Bloomington, IN, Nov. 2016.
[15] Il Yong Chun(†) and Ben Adcock,
“Compressed sensing and parallel acquisition: Optimal uniform and nonuniform recovery guarantees,”
Shannon Centennial Symposium, Ann Arbor, MI, Sep. 2016.
[14] Il Yong Chun(†), Chen Li, and Ben Adcock,
“Sparsity and parallel acquisition: Optimal uniform and nonuniform recovery guarantees,”
in Proc. IEEE Intl. Conf. on Multimedia and Expo (ICME), Workshop on Sparsity and Compressive Sensing in Multimedia (MM-SPARSE), pp. 1–6, Seattle, WA, Jul. 2016. 
[13] Il Yong Chun(†) and Ben Adcock,
“Optimal sparse recovery for multi-sensor measurements,”
in Proc. IEEE Inf. Theory Workshop (ITW), pp. 270–274, Cambridge, UK, Aug. 2016. 
[12] Sumra Bari, Il Yong Chun, Larry J. Leverenz, Eric A. Nauman, and Thomas M. Talavage,
“DTI detection of WM abnormalities using randomization test with complete and incomplete pairs,”
in Proc. Org. for Hum. Brain Mapp. (OHBM), Honolulu, HI, Jun. 2015.
[11] Ikbeom Jang, Il Yong Chun, Larry J. Leverenz, Eric A. Nauman, and Thomas M. Talavage,
“DWI detection of WM abnormality and relation with collision events in high school athletes,”
in Proc. Org. for Hum. Brain Mapp. (OHBM), Honolulu, HI, Jun. 2015.
[10] Ikbeom Jang, Il Yong Chun, Larry J. Leverenz, Eric A. Nauman, and Thomas M. Talavage,
“Robust detection of axonal abnormalities in high school collision-sport athletes: Longitudinal single subject analysis,”
in Proc. Intl. Soc. Mag. Res. Med. (ISMRM), Toronto, ON, May 2015.
[9] Il Yong Chun(†), Ben Adcock, and Thomas M. Talavage,
“Efficient compressed sensing SENSE parallel MRI reconstruction with joint sparsity promotion and mutual incoherence enhancement,”
in Proc. IEEE Eng. Med. Biol. Conf. (EMBC), pp. 2424–2427, Chicago, IL, Aug. 2014.
[8] Il Yong Chun(†), Ben Adcock, and Thomas M. Talavage,
“Non-convex compressed sensing CT reconstruction based on tensor discrete Fourier slice theorem,”
in Proc. IEEE Eng. Med. Biol. Conf. (EMBC), pp. 5141–5144, Chicago, IL, Aug. 2014.
[7] Il Yong Chun(†), Allan Diaz, Sijia Qiu, Larry J. Leverenz, Eric A. Nauman, and Thomas M. Talavage,
“DTI detection of symptomatic and asymptomatic injury due to repetitive hit exposures,”
IN Neuroimaging Symp., Bloomington, IN, Oct. 2013.
[6] Il Yong Chun(†) and Thomas M. Talavage,
“Efficient compressed sensing statistical X-ray/CT reconstruction from fewer measurements,”
in Proc. Intl. Mtg. on Fully 3D Image Recon. in Rad. and Nuc. Med. (Fully 3D), pp. 30–33, Lake Tahoe, CA, Jun. 2013.
[5] Il Yong Chun(†), Allan Diaz, Xiaodong Li, Yun Jang Jin, Larry J. Leverenz, Eric A. Nauman, and Thomas M. Talavage,
“DTI detection of symptomatic and asymptomatic injury due to repetitive head blows,”
in Proc. Org. for Hum. Brain Mapp. (OHBM), Seattle, WA, Jun. 2013.
[4] Il Yong Chun(†) and Thomas M. Talavage,
“Fast non-convex statistical compressed sensing MRI reconstruction based on approximated Lp(0<p<1)-quasi-norm with fewer measurements than using L1-norm,”
in Proc. Intl. Soc. Mag. Res. Med. (ISMRM), Salt Lake City, UT, Apr. 2013.
[3] Il Yong Chun(†) and Thomas M. Talavage,
“Edge-preserving non-iterative MAP SENSE MRI reconstruction,”
in Proc. Intl. Soc. Mag. Res. Med. (ISMRM), Salt Lake City, UT, Apr. 2013.
[2] Il Yong Chun(†) and Thomas M. Talavage,
“Sparse Tikhonov-regularized SENSE MRI reconstruction,”
in Proc. Intl. Soc. Mag. Res. Med. (ISMRM), Salt Lake City, UT, Apr. 2013.
[1] Il Yong Chun(†), Allan Diaz, Yun Jang Jin, Xiaodong Li, Larry J. Leverenz, Eric A. Nauman, and Thomas M. Talavage,
“Robust detection of progressive white matter abnormalities in mTBI using DW-MRI,”
in Proc. Intl. Soc. Mag. Res. Med. (ISMRM), Salt Lake City, UT, Apr. 2013.

bottom of page