Efficient Learning of Image Super-Resolution and Compression Artifact Removal with Semi-Local Gaussian Processes

Cited 32 time in webofscience Cited 0 time in scopus
  • Hit : 257
  • Download : 0
Improving the quality of degraded images is a key problem in image processing, but the breadth of the problem leads to domain-specific approaches for tasks such as super-resolution and compression artifact removal. Recent approaches have shown that a general approach is possible by learning application-specific models from examples; however, learning models sophisticated enough to generate high-quality images is computationally expensive, and so specific per-application or per-dataset models are impractical. To solve this problem, we present an efficient semi-local approximation scheme to large-scale Gaussian processes. This allows efficient learning of task-specific image enhancements from example images without reducing quality. As such, our algorithm can be easily customized to specific applications and datasets, and we show the efficiency and effectiveness of our approach across five domains: single-image super-resolution for scene, human face, and text images, and artifact removal in JPEG- and JPEG 2000-encoded images.
Publisher
IEEE COMPUTER SOC
Issue Date
2015-09
Language
English
Article Type
Article
Keywords

CODED IMAGES; REGRESSION; RECONSTRUCTION; LIMITS; JPEG; DCT

Citation

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.37, no.9, pp.1792 - 1805

ISSN
0162-8828
DOI
10.1109/TPAMI.2015.2389797
URI
http://hdl.handle.net/10203/200576
Appears in Collection
CS-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 32 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0