<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-21T02:02:44Z</responseDate><request verb="GetRecord" identifier="oai:macsphere.mcmaster.ca:11375/32250" metadataPrefix="dim">https://prod-ms-be.lib.mcmaster.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:macsphere.mcmaster.ca:11375/32250</identifier><datestamp>2026-09-24T07:15:46Z</datestamp><setSpec>com_11375_271</setSpec><setSpec>col_11375_272</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:doc="http://www.lyncode.com/xoai" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="advisor">Chen, Jun</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="author">Mousavi, Seyed Amirreza</dim:field>
   <dim:field mdschema="dc" element="contributor" qualifier="department" lang="en_US">Electrical and Computer Engineering</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2025-08-26T19:47:49Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2025-08-26T19:47:49Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2025</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">http://hdl.handle.net/11375/32250</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://doi.org/10.71548/13495</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract" lang="en_US">While deep learning techniques have significantly advanced the field of shadow&#xd;
removal, a considerable number of current methods depend on shadow masks,&#xd;
which are often challenging to acquire accurately. This reliance on masks restricts&#xd;
their ability to generalize effectively to unconstrained real-world scenarios. To address&#xd;
this limitation, we introduce ReHiT, an efficient mask-free shadow removal&#xd;
framework that leverages a hybrid CNN-Transformer architecture, guided by the&#xd;
principles of Retinex theory. Our approach begins with a dual-branch pipeline&#xd;
designed to model the reflectance and illumination components of an image separately.&#xd;
Each of these components is then processed and restored by our novel&#xd;
Illumination-Guided Hybrid CNN-Transformer (IG-HCT) module. Furthermore,&#xd;
in addition to incorporating CNN-based blocks that excel at learning residual&#xd;
dense features and performing multi-scale semantic fusion, we have developed the&#xd;
Illumination-Guided Histogram Transformer Block (IGHB). This specialized block&#xd;
is designed to effectively handle the complexities of non-uniform illumination and&#xd;
spatially intricate shadow patterns. Comprehensive experiments conducted on&#xd;
several standard benchmark datasets demonstrate the superior performance of&#xd;
our proposed method compared to existing mask-free techniques. Notably, our&#xd;
solution achieves competitive results while boasting one of the smallest parameter&#xd;
counts and fastest inference speeds among the state-of-the-art models. This highlights&#xd;
the practical applicability of our method for real-world applications where&#xd;
computational resources may be constrained.</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degreetype" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="degree" lang="en_US">Master of Science in Electrical and Computer Engineering (MSECE)</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso" lang="en_US">en</dim:field>
   <dim:field mdschema="dc" element="subject" lang="en_US">Shadow removal</dim:field>
   <dim:field mdschema="dc" element="title" lang="en_US">ReHiT: Retinex-guided Histogram Transformer for Mask-free Shadow Removal</dim:field>
   <dim:field mdschema="dc" element="type" lang="en_US">Thesis</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim></metadata></record></GetRecord></OAI-PMH>