Welcome to the CIG Lab
The Computational Imaging Group (CIG) at the Skolkovo Institute of Science and Technology pursues research on the development of new mathematical tools and algorithms for the advanced processing and reconstruction of digital images of various types and origin, including biomedical and industrial ones.
Our research mainly focuses on the development of computational methods that enable new imaging capabilities. In particular, we aim to leverage the advances in machine and deep learning, optimization and statistical inference to design new models and algorithms for modern imaging systems.
Broadly speaking, our current research interests lie in the following areas:
- Computational imaging
- Deep learning techniques for image reconstruction
- Statistical image modeling
- Variational and PDE methods
- Optimization techniques for large-scale problems
- Bayesian estimation and inference
- Multiscale image analysis
- Inverse problems in computer vision and image processing with applications in digital photography, biomicroscopy, remote sensing, medical and astronomical imaging
(see Research).
We are looking for passionate new PhD students, Postdocs, and Master students to join the team (more info) !
We are grateful for funding from Skoltech.
News
2018'Deep Image Demosaicking using a Cascade of Convolutional Residual Denoising Networks', Filippos Kokkinos, and Stamatios Lefkimmiatis, Springer, European Conference on Computer Vision (ECCV’18), Munich, Germany, Sept. 2018
2018'Universal Denoising Networks-A Novel CNN Architecture for Image Denoising', Stamatios Lefkimmiatis, IEEE Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA (June 2018)
2017Stamatios Lefkimmiatis et al., IEEE Signal Processing Society Best Paper Award for the journal paper 'Hessian-Based Norm Regularization for Image Restoration With Biomedical Applications' IEEE Transactions on Image Processing, Volume 21, No. 3, March 2012