{"id":{"repo_id":"mcmaster","oai_identifier":"oai:macsphere.mcmaster.ca:11375/23979"},"canonical_url":"https://search.ndltd.org/etd/mcmaster/oai:macsphere.mcmaster.ca:11375/23979","repository":{"repo_id":"mcmaster","name":"McMaster University","base_url":"https://macsphere.mcmaster.ca/server/oai/request"},"display":{"title":"Generic Model-Agnostic Convolutional Neural Networks for Single Image Dehazing","abstract":"Haze and smog are among the most common environmental factors impacting image quality and, therefore, image analysis. In this paper, I propose an end-to-end generative method for single image dehazing problem. It is based on fully convolutional network and effective network structures to recognize haze structure in input images and restore clear, haze-free ones. The proposed method is agnostic in the sense that it does not explore the atmosphere scattering model, it makes use of convolutional networks advantage in feature extraction and transfer instead. Somewhat surprisingly, it achieves superior performance relative to all existing state-of-the-art methods for image dehazing even on SOTS outdoor images, which are synthesized using the atmosphere scattering model. In order to improve its weakness in indoor hazy images and enhance the dehazed image's visual quality, a lightweight parallel network is put forward. It employs a different convolution strategy that extracts features with larger reception field to generate a complementary image. With the help of a parallel stream, the fusion of the two outputs performs better in PSNR and SSIM than other methods.","abstract_html":"Haze and smog are among the most common environmental factors impacting image quality and, therefore, image analysis. In this paper, I propose an end-to-end generative method for single image dehazing problem. It is based on fully convolutional network and effective network structures to recognize haze structure in input images and restore clear, haze-free ones. The proposed method is agnostic in the sense that it does not explore the atmosphere scattering model, it makes use of convolutional networks advantage in feature extraction and transfer instead. Somewhat surprisingly, it achieves superior performance relative to all existing state-of-the-art methods for image dehazing even on SOTS outdoor images, which are synthesized using the atmosphere scattering model. In order to improve its weakness in indoor hazy images and enhance the dehazed image&#x27;s visual quality, a lightweight parallel network is put forward. It employs a different convolution strategy that extracts features with larger reception field to generate a complementary image. With the help of a parallel stream, the fusion of the two outputs performs better in PSNR and SSIM than other methods.","abstract_has_math":false,"creators":["Liu, Zheng"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Electrical and Computer Engineering","school":null,"contributors":[],"advisors":["Chen, Jun"],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018","date_published":"2018","updated_at":"2026-11-18T19:38:35Z","subjects":["image dehazing","deep learning"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.71548/21340"],"render_values":[{"text":"https://doi.org/10.71548/21340","href":"https://doi.org/10.71548/21340","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11375/23979","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"http://hdl.handle.net/11375/23979","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://macsphere.mcmaster.ca/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Amacsphere.mcmaster.ca%3A11375%2F23979","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Chen, Jun"]},{"key":"dc:contributor.department","label":"Department","values":["Electrical and Computer Engineering"]},{"key":"dc:creator","label":"Author","values":["Liu, Zheng"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2019-03-08T20:54:32Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2019-03-08T20:54:32Z"]},{"key":"dc:date.issued","label":"Date","values":["2018"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["image dehazing","deep learning"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/11375/23979","https://doi.org/10.71548/21340"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Haze and smog are among the most common environmental factors impacting image quality and, therefore, image analysis. In this paper, I propose an end-to-end generative method for single image dehazing problem. It is based on fully convolutional network and effective network structures to recognize haze structure in input images and restore clear, haze-free ones. The proposed method is agnostic in the sense that it does not explore the atmosphere scattering model, it makes use of convolutional networks advantage in feature extraction and transfer instead. Somewhat surprisingly, it achieves superior performance relative to all existing state-of-the-art methods for image dehazing even on SOTS outdoor images, which are synthesized using the atmosphere scattering model. In order to improve its weakness in indoor hazy images and enhance the dehazed image's visual quality, a lightweight parallel network is put forward. It employs a different convolution strategy that extracts features with larger reception field to generate a complementary image. With the help of a parallel stream, the fusion of the two outputs performs better in PSNR and SSIM than other methods."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Applied Science (MASc)"]},{"key":"dc:title","label":"Title","values":["Generic Model-Agnostic Convolutional Neural Networks for Single Image Dehazing"]},{"key":"others:access_status","label":"Others Access Status","values":["open.access"]}]}],"canonical_facts":{"dc:contributor.advisor":["Chen, Jun"],"dc:contributor.department":["Electrical and Computer Engineering"],"dc:creator":["Liu, Zheng"],"dc:date.accessioned":["2019-03-08T20:54:32Z"],"dc:date.available":["2019-03-08T20:54:32Z"],"dc:date.issued":["2018"],"dc:description.abstract":["Haze and smog are among the most common environmental factors impacting image quality and, therefore, image analysis. In this paper, I propose an end-to-end generative method for single image dehazing problem. It is based on fully convolutional network and effective network structures to recognize haze structure in input images and restore clear, haze-free ones. The proposed method is agnostic in the sense that it does not explore the atmosphere scattering model, it makes use of convolutional networks advantage in feature extraction and transfer instead. Somewhat surprisingly, it achieves superior performance relative to all existing state-of-the-art methods for image dehazing even on SOTS outdoor images, which are synthesized using the atmosphere scattering model. In order to improve its weakness in indoor hazy images and enhance the dehazed image's visual quality, a lightweight parallel network is put forward. It employs a different convolution strategy that extracts features with larger reception field to generate a complementary image. With the help of a parallel stream, the fusion of the two outputs performs better in PSNR and SSIM than other methods."],"dc:description.degree":["Master of Applied Science (MASc)"],"dc:identifier.uri":["http://hdl.handle.net/11375/23979","https://doi.org/10.71548/21340"],"dc:language.iso":["en"],"dc:subject":["image dehazing","deep learning"],"dc:title":["Generic Model-Agnostic Convolutional Neural Networks for Single Image Dehazing"],"dc:type":["Thesis"],"others:access_status":["open.access"]},"updated_at":"2026-11-18T19:38:35Z"}