{"id":{"repo_id":"mcmaster","oai_identifier":"oai:macsphere.mcmaster.ca:11375/26881"},"canonical_url":"https://search.ndltd.org/etd/mcmaster/oai:macsphere.mcmaster.ca:11375/26881","repository":{"repo_id":"mcmaster","name":"McMaster University","base_url":"https://macsphere.mcmaster.ca/server/oai/request"},"display":{"title":"AWNet: Attentive Wavelet Network for Image ISP","abstract":"As the revolutionary improvement being made on the performance of smartphones over the last decade, mobile photography becomes one of the most common practices among the majority of smartphone users. However, due to the limited size of camera sensors on phone, the photographed image is still visually distinct from the one taken by the digital single-lens reflex (DSLR) camera. To narrow this performance gap, one way is to redesign the camera image signal processor (ISP) to improve the image quality. Owing to the rapid rise of deep learning, recent works resort to the deep convolutional neural network (CNN) to develop a sophisticated data-driven ISP that directly maps the phone-captured image to the DSLR-captured one. In this paper, we introduce a novel network that utilizes the attention mechanism and wavelet transform, dubbed AWNet, to tackle this learnable image ISP problem. By adding the wavelet transform, our proposed method enables us to restore favorable image details from RAW information and achieve a larger receptive field without compromising computational efficiency. The global context block is adopted in our method to learn the non-local color mapping for the generation of appealing RGB images. More importantly, this block alleviates the influence of image misalignment occurred on the provided dataset. Experimental results demonstrate the superiorities of our design in both qualitative and quantitative measurements.","abstract_html":"As the revolutionary improvement being made on the performance of smartphones over the last decade, mobile photography becomes one of the most common practices among the majority of smartphone users. However, due to the limited size of camera sensors on phone, the photographed image is still visually distinct from the one taken by the digital single-lens reflex (DSLR) camera. To narrow this performance gap, one way is to redesign the camera image signal processor (ISP) to improve the image quality. Owing to the rapid rise of deep learning, recent works resort to the deep convolutional neural network (CNN) to develop a sophisticated data-driven ISP that directly maps the phone-captured image to the DSLR-captured one. In this paper, we introduce a novel network that utilizes the attention mechanism and wavelet transform, dubbed AWNet, to tackle this learnable image ISP problem. By adding the wavelet transform, our proposed method enables us to restore favorable image details from RAW information and achieve a larger receptive field without compromising computational efficiency. The global context block is adopted in our method to learn the non-local color mapping for the generation of appealing RGB images. More importantly, this block alleviates the influence of image misalignment occurred on the provided dataset. Experimental results demonstrate the superiorities of our design in both qualitative and quantitative measurements.","abstract_has_math":false,"creators":["Dai, Linhui Jr"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":"Electrical and Computer Engineering","school":null,"contributors":[],"advisors":["Chen, Jun Jr"],"committee_chairs":[],"committee_members":[],"year":2021,"date_issued":"2021","date_published":"2021","updated_at":"2026-11-18T19:36:54Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.71548/17456"],"render_values":[{"text":"https://doi.org/10.71548/17456","href":"https://doi.org/10.71548/17456","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11375/26881","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"http://hdl.handle.net/11375/26881","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%2F26881","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Chen, Jun Jr"]},{"key":"dc:contributor.department","label":"Department","values":["Electrical and Computer Engineering"]},{"key":"dc:creator","label":"Author","values":["Dai, Linhui Jr"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2021-09-15T20:18:56Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2021-09-15T20:18:56Z"]},{"key":"dc:date.issued","label":"Date","values":["2021"]},{"key":"dc:type","label":"Dc Type","values":["Thesis","Article"]}]},{"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/11375/26881","https://doi.org/10.71548/17456"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["As the revolutionary improvement being made on the performance of smartphones over the last decade, mobile photography becomes one of the most common practices among the majority of smartphone users. However, due to the limited size of camera sensors on phone, the photographed image is still visually distinct from the one taken by the digital single-lens reflex (DSLR) camera. To narrow this performance gap, one way is to redesign the camera image signal processor (ISP) to improve the image quality. Owing to the rapid rise of deep learning, recent works resort to the deep convolutional neural network (CNN) to develop a sophisticated data-driven ISP that directly maps the phone-captured image to the DSLR-captured one. In this paper, we introduce a novel network that utilizes the attention mechanism and wavelet transform, dubbed AWNet, to tackle this learnable image ISP problem. By adding the wavelet transform, our proposed method enables us to restore favorable image details from RAW information and achieve a larger receptive field without compromising computational efficiency. The global context block is adopted in our method to learn the non-local color mapping for the generation of appealing RGB images. More importantly, this block alleviates the influence of image misalignment occurred on the provided dataset. Experimental results demonstrate the superiorities of our design in both qualitative and quantitative measurements."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Applied Science (MASc)"]},{"key":"dc:title","label":"Title","values":["AWNet: Attentive Wavelet Network for Image ISP"]},{"key":"others:access_status","label":"Others Access Status","values":["open.access"]}]}],"canonical_facts":{"dc:contributor.advisor":["Chen, Jun Jr"],"dc:contributor.department":["Electrical and Computer Engineering"],"dc:creator":["Dai, Linhui Jr"],"dc:date.accessioned":["2021-09-15T20:18:56Z"],"dc:date.available":["2021-09-15T20:18:56Z"],"dc:date.issued":["2021"],"dc:description.abstract":["As the revolutionary improvement being made on the performance of smartphones over the last decade, mobile photography becomes one of the most common practices among the majority of smartphone users. However, due to the limited size of camera sensors on phone, the photographed image is still visually distinct from the one taken by the digital single-lens reflex (DSLR) camera. To narrow this performance gap, one way is to redesign the camera image signal processor (ISP) to improve the image quality. Owing to the rapid rise of deep learning, recent works resort to the deep convolutional neural network (CNN) to develop a sophisticated data-driven ISP that directly maps the phone-captured image to the DSLR-captured one. In this paper, we introduce a novel network that utilizes the attention mechanism and wavelet transform, dubbed AWNet, to tackle this learnable image ISP problem. By adding the wavelet transform, our proposed method enables us to restore favorable image details from RAW information and achieve a larger receptive field without compromising computational efficiency. The global context block is adopted in our method to learn the non-local color mapping for the generation of appealing RGB images. More importantly, this block alleviates the influence of image misalignment occurred on the provided dataset. Experimental results demonstrate the superiorities of our design in both qualitative and quantitative measurements."],"dc:description.degree":["Master of Applied Science (MASc)"],"dc:identifier.uri":["http://hdl.handle.net/11375/26881","https://doi.org/10.71548/17456"],"dc:language.iso":["en"],"dc:title":["AWNet: Attentive Wavelet Network for Image ISP"],"dc:type":["Thesis","Article"],"others:access_status":["open.access"]},"updated_at":"2026-11-18T19:36:54Z"}