{"id":1179538,"date":"2026-07-21T23:33:13","date_gmt":"2026-07-22T06:33:13","guid":{"rendered":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/?post_type=msr-research-item&p=1179538"},"modified":"2026-07-21T23:33:37","modified_gmt":"2026-07-22T06:33:37","slug":"the-photographers-eye-teach-mllms-to-see-and-critique-like-photographers-2","status":"publish","type":"msr-research-item","link":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/publication\/the-photographers-eye-teach-mllms-to-see-and-critique-like-photographers-2\/","title":{"rendered":"The Photographer’s Eye: Teach MLLMs to See and Critique like Photographers"},"content":{"rendered":"\n\n\n

“While editing directly from life, photographers have found it too difficult to see simultaneously both the blue and the sky.”<\/em><\/p>\n\n\n\n

\u2014 John Szarkowski, William Eggleston’s Guide<\/em><\/p>\n\n\n\n

Photographer and curator, Szarkowski insightfully revealed one of the notable gaps between general and aesthetic visual understanding: while the former focuses on identifying the factual element in an image (sky), the latter transcends such object identification, viewing it instead as an aesthetic component\u2014a pure color block (blue). Such fundamental distinctions between general (detection, localization, etc.) and aesthetic (color, lighting, composition, etc.) visual understanding present a significant challenge for Multimodal Large Language Models (MLLMs). Although some recent works have made initial explorations, they are often limited to general and basic aesthetic commonsense. As a result, they frequently fall short in real-world scenarios, which require extensive expertise\u2014including photographic techniques, photo pre\/post-processing knowledge, and more\u2014to provide a detailed analysis and description.<\/p>\n\n\n\n

To fundamentally enhance the aesthetics understanding of MLLMs, we first introduce a novel dataset, PhotoCritique<\/strong>, derived from extensive discussions among professional photographers and enthusiasts, and characterized by large scale, expertise, and diversity. Then, to better learn visual aesthetics from PhotoCritique, we further propose a novel model, PhotoEye<\/strong>, featuring a language-guided multi-view vision fusion mechanism to understand image aesthetics from multiple perspectives. Finally, we present a novel benchmark, PhotoBench<\/strong>, a comprehensive and professional benchmark for aesthetic visual understanding. On existing benchmarks and PhotoBench, our model demonstrates clear advantages over existing models.<\/p>\n","protected":false},"excerpt":{"rendered":"

“While editing directly from life, photographers have found it too difficult to see simultaneously both the blue and the sky.” \u2014 John Szarkowski, William Eggleston’s Guide Photographer and curator, Szarkowski insightfully revealed one of the notable gaps between general and aesthetic visual understanding: while the former focuses on identifying the factual element in an image […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","msr-author-ordering":[{"type":"user_nicename","value":"Daiqing Qi","user_id":"44245"},{"type":"text","value":"H Zhao","user_id":0},{"type":"text","value":"J Shi","user_id":0},{"type":"text","value":"S Jenni","user_id":0},{"type":"text","value":"Y Fan","user_id":0},{"type":"text","value":"F Dernoncourt","user_id":0},{"type":"text","value":"S Cohen","user_id":0},{"type":"text","value":"S Li","user_id":0}],"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","msr_doi":"","msr_arxiv_id":"","msr_mag_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_release_tracker_id":"","msr_highlight_type":"","msr_date_display_format":"","msr_main_download_label":"","msr_external_link_label":"","msr_doi_label":"","msr_published_date":"2025","msr_startdate":"","msr_presentation_date":"","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_year":2025,"msr_month":0,"msr_day":0,"msr_microsoftintellectualproperty":false,"msr_pub_id":"","msr_publication_uploader":[],"msr_related_uploader":[],"msr_original_fields_of_study":[],"msr_s2_paper_id":"","msr_s2_pdf_url":"","msr_citation_count_updated":"","msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13556],"msr-publication-type":[193716],"msr-publisher":[],"msr-publication-cta":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[270460],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1179538","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2025","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":0,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[],"msr_related_uploader":[],"msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"user_nicename","value":"Daiqing Qi","user_id":44245,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Daiqing Qi"},{"type":"text","value":"H Zhao","user_id":0,"rest_url":false},{"type":"text","value":"J Shi","user_id":0,"rest_url":false},{"type":"text","value":"S Jenni","user_id":0,"rest_url":false},{"type":"text","value":"Y Fan","user_id":0,"rest_url":false},{"type":"text","value":"F Dernoncourt","user_id":0,"rest_url":false},{"type":"text","value":"S Cohen","user_id":0,"rest_url":false},{"type":"text","value":"S Li","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"inproceedings","related_content":[],"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1179538","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":3,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1179538\/revisions"}],"predecessor-version":[{"id":1179541,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1179538\/revisions\/1179541"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1179538"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=1179538"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1179538"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1179538"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1179538"},{"taxonomy":"msr-publication-cta","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-cta?post=1179538"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1179538"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1179538"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1179538"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=1179538"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1179538"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1179538"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1179538"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1179538"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}