Natural image denoising with convolutional networks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

392 Scopus citations

Abstract

We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedure that synthesizes training samples from specific noise models. We demonstrate this approach on the challenging problem of natural image denoising. Using a test set with a hundred natural images, we find that convolutional networks provide comparable and in some cases superior performance to state of the art wavelet and Markov random field (MRF) methods. Moreover, we find that a convolutional network offers similar performance in the blind denoising setting as compared to other techniques in the non-blind setting. We also show how convolutional networks are mathematically related to MRF approaches by presenting a mean field theory for an MRF specially designed for image denoising. Although these approaches are related, convolutional networks avoid computational difficulties in MRF approaches that arise from probabilistic learning and inference. This makes it possible to learn image processing architectures that have a high degree of representational power (we train models with over 15,000 parameters), but whose computational expense is significantly less than that associated with inference in MRF approaches with even hundreds of parameters.

Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems 21 - Proceedings of the 2008 Conference
Pages769-776
Number of pages8
StatePublished - Dec 1 2009
Externally publishedYes
Event22nd Annual Conference on Neural Information Processing Systems, NIPS 2008 - Vancouver, BC, Canada
Duration: Dec 8 2008Dec 11 2008

Publication series

NameAdvances in Neural Information Processing Systems 21 - Proceedings of the 2008 Conference

Other

Other22nd Annual Conference on Neural Information Processing Systems, NIPS 2008
CountryCanada
CityVancouver, BC
Period12/8/0812/11/08

All Science Journal Classification (ASJC) codes

  • Information Systems

Fingerprint Dive into the research topics of 'Natural image denoising with convolutional networks'. Together they form a unique fingerprint.

  • Cite this

    Jain, V., & Seung, H. S. (2009). Natural image denoising with convolutional networks. In Advances in Neural Information Processing Systems 21 - Proceedings of the 2008 Conference (pp. 769-776). (Advances in Neural Information Processing Systems 21 - Proceedings of the 2008 Conference).