{"id":"https://openalex.org/W7123545196","doi":"https://doi.org/10.48550/arxiv.2601.07209","title":"SIRR-LMM: Single-image Reflection Removal via Large Multimodal Model","display_name":"SIRR-LMM: Single-image Reflection Removal via Large Multimodal Model","publication_year":2026,"publication_date":"2026-01-12","ids":{"openalex":"https://openalex.org/W7123545196","doi":"https://doi.org/10.48550/arxiv.2601.07209"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2601.07209","doi":"https://doi.org/10.48550/arxiv.2601.07209","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.07209","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2601.07209","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5122925752","display_name":"Yu Guo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110454582","display_name":"Zhiqiang Lao","orcid":"https://orcid.org/0009-0001-3866-2275","observed_orcids":["https://orcid.org/0009-0001-3866-2275"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lao, Zhiqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101233664","display_name":"Xiyun Song","orcid":"https://orcid.org/0009-0006-3114-7322","observed_orcids":["https://orcid.org/0009-0006-3114-7322"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Xiyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122989910","display_name":"Yubin Zhou","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yubin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109800849","display_name":"Heather Yu","orcid":"https://orcid.org/0009-0008-4793-7585","observed_orcids":["https://orcid.org/0009-0008-4793-7585"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Heather","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.6884999871253967,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11019","display_name":"Image Enhancement Techniques","score":0.6884999871253967,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.13979999721050262,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.050599999725818634,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/single-image-reflection-removal","display_name":"single image reflection removal","score":0.9900000095367432},{"id":"https://openalex.org/keywords/glass-surfaces","display_name":"glass surfaces","score":0.597000002861023},{"id":"https://openalex.org/keywords/reflection-separation","display_name":"reflection separation","score":0.4880000054836273},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.7710000276565552},{"id":"https://openalex.org/keywords/path-tracing","display_name":"path tracing","score":0.8330000042915344},{"id":"https://openalex.org/keywords/large-multimodal-models","display_name":"large multimodal models","score":0.8840000033378601},{"id":"https://openalex.org/keywords/low-rank-adaptation","display_name":"low-rank adaptation","score":0.9549999833106995}],"concepts":[{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.6880999803543091},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6523000001907349},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6158999800682068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6126000285148621},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6010000109672546},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.37929999828338623},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C108597893","wikidata":"https://www.wikidata.org/wiki/Q663650","display_name":"Reflectivity","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C151596937","wikidata":"https://www.wikidata.org/wiki/Q856980","display_name":"Bidirectional reflectance distribution function","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2601.07209","doi":"https://doi.org/10.48550/arxiv.2601.07209","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.07209","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2601.07209","doi":"https://doi.org/10.48550/arxiv.2601.07209","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.07209","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Glass":[0],"surfaces":[1],"create":[2,49],"complex":[3],"interactions":[4],"of":[5,67],"reflected":[6],"and":[7,60,85,105],"transmitted":[8],"light,":[9],"making":[10],"single-image":[11],"reflection":[12,52,103],"removal":[13,104],"(SIRR)":[14],"challenging.":[15],"Existing":[16],"datasets":[17],"suffer":[18],"from":[19],"limited":[20],"physical":[21],"realism":[22],"in":[23,29],"synthetic":[24,35],"data":[25],"or":[26],"insufficient":[27],"scale":[28],"real":[30,45],"captures.":[31],"We":[32],"introduce":[33],"a":[34,78],"dataset":[36],"generation":[37],"framework":[38],"that":[39],"path-traces":[40],"3D":[41],"glass":[42,56],"models":[43],"over":[44],"background":[46],"imagery":[47],"to":[48,100,109],"physically":[50],"accurate":[51],"scenarios":[53],"with":[54],"varied":[55],"properties,":[57],"camera":[58],"settings,":[59],"post-processing":[61],"effects.":[62],"To":[63],"leverage":[64],"the":[65,74,87],"capabilities":[66],"Large":[68],"Multimodal":[69],"Model":[70],"(LMM),":[71],"we":[72],"concatenate":[73],"image":[75],"layers":[76],"into":[77],"single":[79],"composite":[80],"input,":[81],"apply":[82],"joint":[83],"captioning,":[84],"fine-tune":[86],"model":[88],"using":[89],"task-specific":[90],"LoRA":[91],"rather":[92],"than":[93],"full-parameter":[94],"training.":[95],"This":[96],"enables":[97],"our":[98],"approach":[99],"achieve":[101],"improved":[102],"separation":[106],"performance":[107],"compared":[108],"state-of-the-art":[110],"methods.":[111]},"counts_by_year":[],"updated_date":"2026-09-21T07:43:02.447757","created_date":"2026-01-14T00:00:00"}