{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/78325"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/78325","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Learning to super-resolve images using self-similarities","abstract":"The single image super-resolution problem entails estimating a high-resolution version of a low-resolution image. Recent studies have shown that high resolution versions of the patches of a given low-resolution image are likely to be found within the given image itself. This recurrence of patches across scales in an image forms the basis of self-similarity driven algorithms for image super-resolution. Self-similarity driven approaches have the appeal that they do not require any external training set; the mapping from low-resolution to high-resolution is obtained using the cross scale patch recurrence. In this dissertation, we address three important problems in super-resolution, and present novel self-similarity based solutions to them: First, we push the state-of-the-art in terms of super-resolution of fine textural details in the scene. We propose two algorithms that use self-similarity in conjunction with the fact that textures are better characterized by their responses to a set of spatially localized bandpass filters, as compared to intensity values directly. Our proposed algorithms seek self-similarities in the sub-bands of the image, for better synthesizing fine textural details. Second, we address the problem of super-resolving an image in the presence of noise. To this end, we propose the first super-resolution algorithm based on self-similarity that effectively exploits the high-frequency content present in noise (which is ordinarily discarded by denoising algorithms) for synthesizing useful textures in high-resolution. Third, we present an algorithm that is able to better super-resolve images containing geometric regularities such as in urban scenes, cityscapes etc. We do so by extracting planar surfaces and their parameters (mid-level cues) from the scene and exploiting the detected scene geometry for better guiding the self-similarity search process. Apart from the above self-similarity algorithms, this dissertation also presents a novel edge-based super-resolution algorithm that super-resolves an image by learning from training data how edge profiles transform across resolutions. We obtain edge profiles via a detailed and explicit examination of local image structure, which we show to be more robust and accurate as compared to conventional gradient profiles.","abstract_html":"The single image super-resolution problem entails estimating a high-resolution version of a low-resolution image. Recent studies have shown that high resolution versions of the patches of a given low-resolution image are likely to be found within the given image itself. This recurrence of patches across scales in an image forms the basis of self-similarity driven algorithms for image super-resolution. Self-similarity driven approaches have the appeal that they do not require any external training set; the mapping from low-resolution to high-resolution is obtained using the cross scale patch recurrence. In this dissertation, we address three important problems in super-resolution, and present novel self-similarity based solutions to them: First, we push the state-of-the-art in terms of super-resolution of fine textural details in the scene. We propose two algorithms that use self-similarity in conjunction with the fact that textures are better characterized by their responses to a set of spatially localized bandpass filters, as compared to intensity values directly. Our proposed algorithms seek self-similarities in the sub-bands of the image, for better synthesizing fine textural details. Second, we address the problem of super-resolving an image in the presence of noise. To this end, we propose the first super-resolution algorithm based on self-similarity that effectively exploits the high-frequency content present in noise (which is ordinarily discarded by denoising algorithms) for synthesizing useful textures in high-resolution. Third, we present an algorithm that is able to better super-resolve images containing geometric regularities such as in urban scenes, cityscapes etc. We do so by extracting planar surfaces and their parameters (mid-level cues) from the scene and exploiting the detected scene geometry for better guiding the self-similarity search process. Apart from the above self-similarity algorithms, this dissertation also presents a novel edge-based super-resolution algorithm that super-resolves an image by learning from training data how edge profiles transform across resolutions. We obtain edge profiles via a detailed and explicit examination of local image structure, which we show to be more robust and accurate as compared to conventional gradient profiles.","abstract_has_math":false,"creators":["Singh, Abhishek"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"Ph.D.","degree_level":"Dissertation","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Ahuja, Narendra","Forsyth, David A.","Do, Minh N.","Hasegawa-Johnson, Mark A."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2015,"date_issued":"2015-07-22T22:16:03Z","date_published":"2015-07-22T22:16:03Z","updated_at":"2026-07-22T22:26:11Z","subjects":["Self-Similarity","Image Enhancement","Image Super-Resolution"],"languages":[],"rights":["Copyright 2015 Abhishek Singh"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/78325","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Ahuja, Narendra","Forsyth, David A.","Do, Minh N.","Hasegawa-Johnson, Mark A."]},{"key":"dc:creator","label":"Author","values":["Singh, Abhishek"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2015-07-22T22:16:03Z","2015-05","2015-03-06","2015-5"]},{"key":"dc:type","label":"Dc Type","values":["text"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Ph.D."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Self-Similarity","Image Enhancement","Image Super-Resolution"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2015 Abhishek Singh"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/78325"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The single image super-resolution problem entails estimating a high-resolution version of a low-resolution image. Recent studies have shown that high resolution versions of the patches of a given low-resolution image are likely to be found within the given image itself. This recurrence of patches across scales in an image forms the basis of self-similarity driven algorithms for image super-resolution. Self-similarity driven approaches have the appeal that they do not require any external training set; the mapping from low-resolution to high-resolution is obtained using the cross scale patch recurrence. In this dissertation, we address three important problems in super-resolution, and present novel self-similarity based solutions to them: First, we push the state-of-the-art in terms of super-resolution of fine textural details in the scene. We propose two algorithms that use self-similarity in conjunction with the fact that textures are better characterized by their responses to a set of spatially localized bandpass filters, as compared to intensity values directly. Our proposed algorithms seek self-similarities in the sub-bands of the image, for better synthesizing fine textural details. Second, we address the problem of super-resolving an image in the presence of noise. To this end, we propose the first super-resolution algorithm based on self-similarity that effectively exploits the high-frequency content present in noise (which is ordinarily discarded by denoising algorithms) for synthesizing useful textures in high-resolution. Third, we present an algorithm that is able to better super-resolve images containing geometric regularities such as in urban scenes, cityscapes etc. We do so by extracting planar surfaces and their parameters (mid-level cues) from the scene and exploiting the detected scene geometry for better guiding the self-similarity search process. Apart from the above self-similarity algorithms, this dissertation also presents a novel edge-based super-resolution algorithm that super-resolves an image by learning from training data how edge profiles transform across resolutions. We obtain edge profiles via a detailed and explicit examination of local image structure, which we show to be more robust and accurate as compared to conventional gradient profiles.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2015-07-22 without embargo terms","The student, Abhishek Singh, accepted the attached license on 2015-03-06 at 10:36.","The student, Abhishek Singh, submitted this Dissertation for approval on 2015-03-06 at 10:49.","This Dissertation was approved for publication on 2015-03-06 at 16:11.","DSpace SAF Submission Ingestion Package generated from Vireo submission #7738 on 2015-07-22 at 10:30:22","Made available in DSpace on 2015-07-22T22:16:03Z (GMT). No. of bitstreams: 2 Singh_Abhishek.pdf: 41253321 bytes, checksum: 8d9718108354d77053fc1a347c5931bd (MD5) license.txt: 4064 bytes, checksum: 3cf96fae41302ae9cdd1193eb3af01b9 (MD5) Previous issue date: 2015-03-06"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Learning to super-resolve images using self-similarities"]}]}],"canonical_facts":{"dc:contributor":["Ahuja, Narendra","Forsyth, David A.","Do, Minh N.","Hasegawa-Johnson, Mark A."],"dc:creator":["Singh, Abhishek"],"dc:date":["2015-07-22T22:16:03Z","2015-05","2015-03-06","2015-5"],"dc:description":["The single image super-resolution problem entails estimating a high-resolution version of a low-resolution image. Recent studies have shown that high resolution versions of the patches of a given low-resolution image are likely to be found within the given image itself. This recurrence of patches across scales in an image forms the basis of self-similarity driven algorithms for image super-resolution. Self-similarity driven approaches have the appeal that they do not require any external training set; the mapping from low-resolution to high-resolution is obtained using the cross scale patch recurrence. In this dissertation, we address three important problems in super-resolution, and present novel self-similarity based solutions to them: First, we push the state-of-the-art in terms of super-resolution of fine textural details in the scene. We propose two algorithms that use self-similarity in conjunction with the fact that textures are better characterized by their responses to a set of spatially localized bandpass filters, as compared to intensity values directly. Our proposed algorithms seek self-similarities in the sub-bands of the image, for better synthesizing fine textural details. Second, we address the problem of super-resolving an image in the presence of noise. To this end, we propose the first super-resolution algorithm based on self-similarity that effectively exploits the high-frequency content present in noise (which is ordinarily discarded by denoising algorithms) for synthesizing useful textures in high-resolution. Third, we present an algorithm that is able to better super-resolve images containing geometric regularities such as in urban scenes, cityscapes etc. We do so by extracting planar surfaces and their parameters (mid-level cues) from the scene and exploiting the detected scene geometry for better guiding the self-similarity search process. Apart from the above self-similarity algorithms, this dissertation also presents a novel edge-based super-resolution algorithm that super-resolves an image by learning from training data how edge profiles transform across resolutions. We obtain edge profiles via a detailed and explicit examination of local image structure, which we show to be more robust and accurate as compared to conventional gradient profiles.","Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2015-07-22 without embargo terms","The student, Abhishek Singh, accepted the attached license on 2015-03-06 at 10:36.","The student, Abhishek Singh, submitted this Dissertation for approval on 2015-03-06 at 10:49.","This Dissertation was approved for publication on 2015-03-06 at 16:11.","DSpace SAF Submission Ingestion Package generated from Vireo submission #7738 on 2015-07-22 at 10:30:22","Made available in DSpace on 2015-07-22T22:16:03Z (GMT). No. of bitstreams: 2 Singh_Abhishek.pdf: 41253321 bytes, checksum: 8d9718108354d77053fc1a347c5931bd (MD5) license.txt: 4064 bytes, checksum: 3cf96fae41302ae9cdd1193eb3af01b9 (MD5) Previous issue date: 2015-03-06"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/78325"],"dc:rights":["Copyright 2015 Abhishek Singh"],"dc:subject":["Self-Similarity","Image Enhancement","Image Super-Resolution"],"dc:title":["Learning to super-resolve images using self-similarities"],"dc:type":["text"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Dissertation"],"thesis:degree_name":["Ph.D."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:26:11Z"}