Computation plays an important role in modern imaging including medical imaging: Modern imaging systems pose interesting, but challenging problems under non-ideal circumstances. By solving them with the aid of computations, one can see something farther away, something deeper inside, and something much smaller. Signal processing and machine learning are important & powerful tools to tackle them effectively.
Intelligent Computational imaging Lab (ICL) is investigating modern signal processing and machine learning for computation imaging, especially for medical imaging. ICL generalizes the problems posed by computational & medical imaging and solves them so that our solutions can be applied not only to computation imaging itself, but also to low-level computer vision or other areas. ICL is publishing its works in major medical imaging & signal processing journals as well as in major machine learning & computer vision conferences.
Research Interests & Projects
Computational & medical imaging;
Journals & Patents
- K Y Kim, D W Park, K I Kim, S Y Chun, “Task-Aware Variational Adversarial Active Learning,” Accepted to CVPR 2021;
- YJ Kim et al., “PAIP 2019: Liver cancer segmentation challenge,” Medical Image Analysis 67:101854, Jan 2021;
- K Y Kim, S Soltanayev, S Y Chun, “Unsupervised Training Of Deep Low-Dose CT Reconstruction Without Full-Dose CT Images,” IEEE Journal of Selected Topics in Signal Processing 14(6):1112-1125, Oct 2020;
- D W Park, D U Kang, J S Kim, S Y Chun, “Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training,” ECCV, Aug 2020 (spotlight);
- S Y Chun, M P Nguyen, T Q Phan, H V Kim, J A Fessler, Y K Dewaraja, “Algorithms and Analyses for Joint Spectral Image Reconstruction in Y-90 Bremsstrahlung SPECT,” IEEE Transactions on Medical Imaging 39(5):1369-79, May 2020;
- D W Park, Y H Seo, S Y Chun, “Real-Time, Highly Accurate Robotic Grasp Detection using Fully Convolutional Neural Network with Rotation Ensemble Module,” ICRA 9397-9403, May 2020;
- M Zhussip, S Soltanayev, S Y Chun, “Extending Stein’s unbiased risk estimator to train deep denoisers with correlated pairs of noisy images,” NeurIPS, Dec 2019;
- M Zhussip, S Soltanayev, S Y Chun, “Training deep learning based image denoisers from undersampled measurements without ground truth and without image prior,” CVPR 10247-56, Jun 2019;
- S Soltanayev, S Y Chun, “Training Deep Learning based Denoisers without Ground Truth Data,” NeurIPS 3261-3271, Dec 2018;
- H Lee, S Baek, S Y Chun, J H Lee, H J Cho, “Specific visualization of iron-clustered neuromelanin and tissue iron in the human post-mortem substantia nigra using MR relaxometry at 7T,” NeuroImage 172:874-85, May 2018;