2026-09-19T02:36:17Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/73058 2023-07-11 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Huang, Thomas S. Wang, Zhangyang 2015-01-21T19:58:59Z 2015-01-21T19:58:59Z 2014-12 2015-01-21 2014-12 Image super-resolution (SR) aims to estimate of a high-resolution (HR) image from low-resolution (LR) input. Image priors are commonly learned to regularize the ill-posed SR problem, either using external LR-HR pairs or internal similar patterns repeating across di erent scales. We propose joint SR to adaptively combine the advantages of both external and internal SR. We de ne the two loss functions using sparse coding and epitomic matching, respectively. A corresponding adaptive weight is constructed to balance their e ect according to the reconstruction errors. Various image results demonstrate the e ectiveness of the proposed method over the existing state-of-the-art methods, which is also veri ed by our subject evaluation experiment. Item withdrawn by Laura Spradlin (lspradl2@illinois.edu) on 2014-11-19T14:54:13Z Item was in collections: University of Illinois Theses & Dissertations (ID: 1) No. of bitstreams: 1 Wang_Zhangyang.pdf: 17046622 bytes, checksum: 2c728cdcc0b1a10f0b023234e3a8a244 (MD5) Made available in DSpace on 2015-01-21T19:58:59Z (GMT). No. of bitstreams: 1 Zhangyang_Wang.pdf: 17046622 bytes, checksum: 2c728cdcc0b1a10f0b023234e3a8a244 (MD5) Embargo set by: Seth Robbins for item 73247 Lift date: 2017-01-21T19:59:39Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system Open http://hdl.handle.net/2142/73058 en Copyright 2014 Zhangyang Wang super-resolution example-based learning sparse coding epitomic matching subject evaluation Learning image super resolution from joint examples text Electrical & Computer Eng 1933 Electrical & Computer Engr 1200 University of Illinois at Urbana-Champaign Thesis M.S. MS:Electr & Computer Eng-UIUC 10KS1200MS