EE Student Information

The Department of Electrical Engineering supports Black Lives Matter. Read more.

• • • • •

EE Student Information, Spring Quarter through Academic Year 2020-2021: FAQs and Updated EE Course List.

Updates will be posted on this page, as well as emailed to the EE student mail list.

Please see Stanford University Health Alerts for course and travel updates.

As always, use your best judgement and consider your own and others' well-being at all times.

ISL Colloquium presents "Fully Convolutional Pixelwise Context-Adaptive Denoiser"

Fully Convolutional Pixelwise Context-Adaptive Denoiser
Friday, February 21, 2020 - 1:15pm
Packard 202
Prof. Taesup Moon (Sungkyunkwan University)
Abstract / Description: 

Denoising is a classical problem in signal processing and information theory, and various different methods have been applied to tackle the problem for several decades. Recently, supervised-trained neural network-based methods have achieved impressive denoising performances, significantly surpassing those of the classical approaches, such as prior- or optimization-based denoisers. However, there are two drawbacks on those methods; they are not adaptive, i.e., the neural- network cannot correct itself when distributional mismatch between training and test data exists, and they require clean source data and exact noise model for training, which is not always possible in some practical scenarios. In this talk, I will introduce a framework that tries to tackle above two drawbacks jointly, based on an unbiased estimate of the loss of a particular class of pixelwise context- adaptive denoisers. Using the framework and neural networks to learn the denoisers, I show the resulting image denoiser can adapt to mismatched distributions in the data solely based on the given noisy images, and achieve the state-of-the-art performances on several benchmark datasets. Moreover, combined with the standard noise transform/estimation techniques, I will show that our denoiser can be completely blindly trained only with the noisy images (and without exact noise model) and yet be very effective for denoising more sophisticated, source-dependent real-world noise, e.g., Poisson- Gaussian noise.

This is a joint work with my students, Sungmin Cha and Jaeseok Byun at SKKU.


Taesup Moon received the B.S. degree in electrical engineering from Seoul National University, Seoul, Korea, in 2002 and the M.S. and Ph.D. degrees in electrical engineering from Stanford University, Stanford, CA, USA, in 2004 and 2008, respectively. From 2008 to 2012, he was a Scientist at Yahoo! Labs, Sunnyvale, CA, and he held a Post-Doctoral Researcher appointment with the Department of Statistics, UC Berkeley from 2012 to 2013. From 2013 to 2015, he was a Research Staff Member with Samsung Advanced Institute of Technology. From 2015 to 2017, he was an Assistant Professor at the Department of Information and Communication Engineering, Daegu-Gyeongbuk Institute of Science and Technology (DGIST). Currently, he is an Associate Professor at the Department of Electrical and Computer Engineering, Sungkyunkwan University (SKKU), Suwon, South Korea.

His current research interests are in machine/deep learning, signal processing, information theory, and various data science applications.