{"id":{"repo_id":"mcmaster","oai_identifier":"oai:macsphere.mcmaster.ca:11375/32250"},"canonical_url":"https://search.ndltd.org/etd/mcmaster/oai:macsphere.mcmaster.ca:11375/32250","repository":{"repo_id":"mcmaster","name":"McMaster University","base_url":"https://macsphere.mcmaster.ca/server/oai/request"},"display":{"title":"ReHiT: Retinex-guided Histogram Transformer for Mask-free Shadow Removal","abstract":"While deep learning techniques have significantly advanced the field of shadow removal, a considerable number of current methods depend on shadow masks, which are often challenging to acquire accurately. This reliance on masks restricts their ability to generalize effectively to unconstrained real-world scenarios. To address this limitation, we introduce ReHiT, an efficient mask-free shadow removal framework that leverages a hybrid CNN-Transformer architecture, guided by the principles of Retinex theory. Our approach begins with a dual-branch pipeline designed to model the reflectance and illumination components of an image separately. Each of these components is then processed and restored by our novel Illumination-Guided Hybrid CNN-Transformer (IG-HCT) module. Furthermore, in addition to incorporating CNN-based blocks that excel at learning residual dense features and performing multi-scale semantic fusion, we have developed the Illumination-Guided Histogram Transformer Block (IGHB). This specialized block is designed to effectively handle the complexities of non-uniform illumination and spatially intricate shadow patterns. Comprehensive experiments conducted on several standard benchmark datasets demonstrate the superior performance of our proposed method compared to existing mask-free techniques. Notably, our solution achieves competitive results while boasting one of the smallest parameter counts and fastest inference speeds among the state-of-the-art models. This highlights the practical applicability of our method for real-world applications where computational resources may be constrained.","abstract_html":"While deep learning techniques have significantly advanced the field of shadow removal, a considerable number of current methods depend on shadow masks, which are often challenging to acquire accurately. This reliance on masks restricts their ability to generalize effectively to unconstrained real-world scenarios. To address this limitation, we introduce ReHiT, an efficient mask-free shadow removal framework that leverages a hybrid CNN-Transformer architecture, guided by the principles of Retinex theory. Our approach begins with a dual-branch pipeline designed to model the reflectance and illumination components of an image separately. Each of these components is then processed and restored by our novel Illumination-Guided Hybrid CNN-Transformer (IG-HCT) module. Furthermore, in addition to incorporating CNN-based blocks that excel at learning residual dense features and performing multi-scale semantic fusion, we have developed the Illumination-Guided Histogram Transformer Block (IGHB). This specialized block is designed to effectively handle the complexities of non-uniform illumination and spatially intricate shadow patterns. Comprehensive experiments conducted on several standard benchmark datasets demonstrate the superior performance of our proposed method compared to existing mask-free techniques. Notably, our solution achieves competitive results while boasting one of the smallest parameter counts and fastest inference speeds among the state-of-the-art models. This highlights the practical applicability of our method for real-world applications where computational resources may be constrained.","abstract_has_math":false,"creators":["Mousavi, Seyed Amirreza"],"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":"2026-11-18T19:33:13Z","subjects":["Shadow removal"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://doi.org/10.71548/13495"],"render_values":[{"text":"https://doi.org/10.71548/13495","href":"https://doi.org/10.71548/13495","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/11375/32250","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"http://hdl.handle.net/11375/32250","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%2F32250","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":["Mousavi, Seyed Amirreza"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-08-26T19:47:49Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-08-26T19:47:49Z"]},{"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":["Shadow removal"]}]},{"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/11375/32250","https://doi.org/10.71548/13495"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["While deep learning techniques have significantly advanced the field of shadow removal, a considerable number of current methods depend on shadow masks, which are often challenging to acquire accurately. This reliance on masks restricts their ability to generalize effectively to unconstrained real-world scenarios. To address this limitation, we introduce ReHiT, an efficient mask-free shadow removal framework that leverages a hybrid CNN-Transformer architecture, guided by the principles of Retinex theory. Our approach begins with a dual-branch pipeline designed to model the reflectance and illumination components of an image separately. Each of these components is then processed and restored by our novel Illumination-Guided Hybrid CNN-Transformer (IG-HCT) module. Furthermore, in addition to incorporating CNN-based blocks that excel at learning residual dense features and performing multi-scale semantic fusion, we have developed the Illumination-Guided Histogram Transformer Block (IGHB). This specialized block is designed to effectively handle the complexities of non-uniform illumination and spatially intricate shadow patterns. Comprehensive experiments conducted on several standard benchmark datasets demonstrate the superior performance of our proposed method compared to existing mask-free techniques. Notably, our solution achieves competitive results while boasting one of the smallest parameter counts and fastest inference speeds among the state-of-the-art models. This highlights the practical applicability of our method for real-world applications where computational resources may be constrained."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science in Electrical and Computer Engineering (MSECE)"]},{"key":"dc:title","label":"Title","values":["ReHiT: Retinex-guided Histogram Transformer for Mask-free Shadow Removal"]},{"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":["Mousavi, Seyed Amirreza"],"dc:date.accessioned":["2025-08-26T19:47:49Z"],"dc:date.available":["2025-08-26T19:47:49Z"],"dc:date.issued":["2025"],"dc:description.abstract":["While deep learning techniques have significantly advanced the field of shadow removal, a considerable number of current methods depend on shadow masks, which are often challenging to acquire accurately. This reliance on masks restricts their ability to generalize effectively to unconstrained real-world scenarios. To address this limitation, we introduce ReHiT, an efficient mask-free shadow removal framework that leverages a hybrid CNN-Transformer architecture, guided by the principles of Retinex theory. Our approach begins with a dual-branch pipeline designed to model the reflectance and illumination components of an image separately. Each of these components is then processed and restored by our novel Illumination-Guided Hybrid CNN-Transformer (IG-HCT) module. Furthermore, in addition to incorporating CNN-based blocks that excel at learning residual dense features and performing multi-scale semantic fusion, we have developed the Illumination-Guided Histogram Transformer Block (IGHB). This specialized block is designed to effectively handle the complexities of non-uniform illumination and spatially intricate shadow patterns. Comprehensive experiments conducted on several standard benchmark datasets demonstrate the superior performance of our proposed method compared to existing mask-free techniques. Notably, our solution achieves competitive results while boasting one of the smallest parameter counts and fastest inference speeds among the state-of-the-art models. This highlights the practical applicability of our method for real-world applications where computational resources may be constrained."],"dc:description.degree":["Master of Science in Electrical and Computer Engineering (MSECE)"],"dc:identifier.uri":["http://hdl.handle.net/11375/32250","https://doi.org/10.71548/13495"],"dc:language.iso":["en"],"dc:subject":["Shadow removal"],"dc:title":["ReHiT: Retinex-guided Histogram Transformer for Mask-free Shadow Removal"],"dc:type":["Thesis"],"others:access_status":["open.access"]},"updated_at":"2026-11-18T19:33:13Z"}