{"id":{"repo_id":"mcmaster","oai_identifier":"oai:macsphere.mcmaster.ca:11375/31612"},"canonical_url":"https://search.ndltd.org/etd/mcmaster/oai:macsphere.mcmaster.ca:11375/31612","repository":{"repo_id":"mcmaster","name":"McMaster University","base_url":"https://macsphere.mcmaster.ca/server/oai/request"},"display":{"title":"Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design","abstract":"We present a novel Transformer-based framework for low-light image enhancement, Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design. Our model is built upon a U-Net-style encoder–decoder architecture, where we introduce a customized Hybrid Structure-Guided Feature Extractor (HSGFE) at each scale. The HSGFE integrates three key components: (1) a Dilated Residual Dense Block (DRDB) for effective feature refinement, (2) a Structure-Guided Transformer Block (SGTB) that incorporates structural priors to preserve edges and suppress noise, and (3) a Semantic-Aligned Scale-Aware Module (SAM) to handle multi-scale variations. This design enables our network to enhance low-light images while maintaining structural integrity and reducing color distortion. Extensive experiments show that our method achieves state-of-the-art performance in both quantitative metrics and visual quality. Our approach also achieve top-tier results on standard LLIE benchmarks and ranked second in the NTIRE 2025 Low-Light Image Enhancement Challenge.","abstract_html":"We present a novel Transformer-based framework for low-light image enhancement, Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design. Our model is built upon a U-Net-style encoder–decoder architecture, where we introduce a customized Hybrid Structure-Guided Feature Extractor (HSGFE) at each scale. The HSGFE integrates three key components: (1) a Dilated Residual Dense Block (DRDB) for effective feature refinement, (2) a Structure-Guided Transformer Block (SGTB) that incorporates structural priors to preserve edges and suppress noise, and (3) a Semantic-Aligned Scale-Aware Module (SAM) to handle multi-scale variations. This design enables our network to enhance low-light images while maintaining structural integrity and reducing color distortion. Extensive experiments show that our method achieves state-of-the-art performance in both quantitative metrics and visual quality. Our approach also achieve top-tier results on standard LLIE benchmarks and ranked second in the NTIRE 2025 Low-Light Image Enhancement Challenge.","abstract_has_math":false,"creators":["Min, Yan"],"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":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-11-18T19:32:37Z","subjects":["Computer Vision","Deep Learning","Low Light Image Enhancement"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.71548/12373"],"render_values":[{"text":"https://doi.org/10.71548/12373","href":"https://doi.org/10.71548/12373","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11375/31612","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"http://hdl.handle.net/11375/31612","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%2F31612","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":["Min, Yan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-05-05T16:09:09Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-05-05T16:09:09Z"]},{"key":"dc:date.issued","label":"Date","values":["2025"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer Vision","Deep Learning","Low Light Image Enhancement"]}]},{"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/11375/31612","https://doi.org/10.71548/12373"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["We present a novel Transformer-based framework for low-light image enhancement, Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design. Our model is built upon a U-Net-style encoder–decoder architecture, where we introduce a customized Hybrid Structure-Guided Feature Extractor (HSGFE) at each scale. The HSGFE integrates three key components: (1) a Dilated Residual Dense Block (DRDB) for effective feature refinement, (2) a Structure-Guided Transformer Block (SGTB) that incorporates structural priors to preserve edges and suppress noise, and (3) a Semantic-Aligned Scale-Aware Module (SAM) to handle multi-scale variations. This design enables our network to enhance low-light images while maintaining structural integrity and reducing color distortion. Extensive experiments show that our method achieves state-of-the-art performance in both quantitative metrics and visual quality. Our approach also achieve top-tier results on standard LLIE benchmarks and ranked second in the NTIRE 2025 Low-Light Image Enhancement Challenge."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science in Electrical and Computer Engineering (MSECE)"]},{"key":"dc:title","label":"Title","values":["Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design"]},{"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":["Min, Yan"],"dc:date.accessioned":["2025-05-05T16:09:09Z"],"dc:date.available":["2025-05-05T16:09:09Z"],"dc:date.issued":["2025"],"dc:description.abstract":["We present a novel Transformer-based framework for low-light image enhancement, Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design. Our model is built upon a U-Net-style encoder–decoder architecture, where we introduce a customized Hybrid Structure-Guided Feature Extractor (HSGFE) at each scale. The HSGFE integrates three key components: (1) a Dilated Residual Dense Block (DRDB) for effective feature refinement, (2) a Structure-Guided Transformer Block (SGTB) that incorporates structural priors to preserve edges and suppress noise, and (3) a Semantic-Aligned Scale-Aware Module (SAM) to handle multi-scale variations. This design enables our network to enhance low-light images while maintaining structural integrity and reducing color distortion. Extensive experiments show that our method achieves state-of-the-art performance in both quantitative metrics and visual quality. Our approach also achieve top-tier results on standard LLIE benchmarks and ranked second in the NTIRE 2025 Low-Light Image Enhancement Challenge."],"dc:description.degree":["Master of Science in Electrical and Computer Engineering (MSECE)"],"dc:identifier.uri":["http://hdl.handle.net/11375/31612","https://doi.org/10.71548/12373"],"dc:language.iso":["en"],"dc:subject":["Computer Vision","Deep Learning","Low Light Image Enhancement"],"dc:title":["Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design"],"dc:type":["Thesis"],"others:access_status":["open.access"]},"updated_at":"2026-11-18T19:32:37Z"}