CoChat

Supervised Learning of Image Restoration with Convolutional Networks

The DOI matches its Crossref record; the references it cites are not checked yet.

Abstract

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.

Overview

Integrity signals

Registry

Crossref · 10.1109/iccv.2007.4408909

Cites

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

The citation lists are queued

They are fetched later and appear here then.

References 26 · Cited by 217

Research works printed but not linked: 1

  1. parise, 2005, Learning in markov random fields: An empirical study, Joint Statistical Meeting

Metadata

Authors
Jain, V., Murray, J. F., Roth, F., Turaga, S., Zhigulin, V., Briggman, K. L., Helmstaedter, M. N., Denk, W., & Seung, H. S.
Affiliations
  • Massachusetts Institute of Technology (US)
  • Howard Hughes Medical Institute (US)
  • Max Planck Institute for Medical Research (DE)
Venue
2007 IEEE 11th International Conference on Computer Vision
Publisher
IEEE
Published
2007
Pages
1-8
OpenAlex
W2129981175
Cited by
217
References
26
Citations by year
2025: 5 · 2024: 8 · 2023: 15 · 2022: 9 · 2021: 8 · 2020: 8 · 2019: 9 · 2018: 16 · 2017: 15 · 2016: 19 · 2015: 18 · 2014: 9 · 2013: 20 · 2012: 13
FWCI
9.29
Type
conference paper
Language
en
Open access
closed
Locations
IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image Processing Techniques
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
Keywords
image restoration, convolutional neural networks, supervised learning, electron microscopy images, neural circuits, Markov random fields, conditional random fields, anisotropic diffusion, image segmentation, model complexity, Bayesian inference

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Supervised Learning of Image Restoration with Convolutional Networks. https://app.cochat.ai/papers/10.1109/iccv.2007.4408909
The paper
Jain, V., Murray, J. F., Roth, F., Turaga, S., Zhigulin, V., Briggman, K. L., Helmstaedter, M. N., Denk, W., & Seung, H. S. (2007). Supervised Learning of Image Restoration with Convolutional Networks. 2007 IEEE 11th International Conference on Computer Vision. https://doi.org/10.1109/iccv.2007.4408909

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.