Supervised learning of image restoration with convolutional networks

Viren Jain, Joseph F. Murray, Fabian Roth, Srinivas Turaga, Valentin Zhigulin, Kevin L. Briggman, Moritz N. Helmstaedter, Winfried Denk, H. Sebastian Seung

Research output: Contribution to conferencePaperpeer-review

174 Scopus citations


Convolutional networks have achieved a great deal of success in high-level vision problems such as object recognition. Here we show that they can also be used as a general method for low-level image processing. As an example of our approach, convolutional networks are trained using gradient learning to solve the problem of restoring noisy or degraded images. For our training data, we have used electron microscopic images of neural circuitry with ground truth restorations provided by human experts. On this dataset, Markov random field (MRF), conditional random field (CRF), and anisotropic diffusion algorithms perform about the same as simple thresholding, but superior performance is obtained with a convolutional network containing over 34,000 adjustable parameters. When restored by this convolutional network, the images are clean enough to be used for segmentation, whereas the other approaches fail in this respect. We do not believe that convolutional networks are fundamentally superior to MRFs as a representation for image processing algorithms. On the contrary, the two approaches are closely related. But in practice, it is possible to train complex convolutional networks, while even simple MRF models are hindered by problems with Bayesian learning and inference procedures. Our results suggest that high model complexity is the single most important factor for good performance, and this is possible with convolutional networks.

Original languageEnglish (US)
StatePublished - 2007
Externally publishedYes
Event2007 IEEE 11th International Conference on Computer Vision, ICCV - Rio de Janeiro, Brazil
Duration: Oct 14 2007Oct 21 2007


Other2007 IEEE 11th International Conference on Computer Vision, ICCV
CityRio de Janeiro

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Supervised learning of image restoration with convolutional networks'. Together they form a unique fingerprint.

Cite this