{"id":1181186,"date":"2026-08-10T01:23:47","date_gmt":"2026-08-10T08:23:47","guid":{"rendered":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/publication\/pixel-to-gaussian-ultra-fast-continuous-super-resolution-with-2d-gaussian-modeling\/"},"modified":"2026-08-15T11:06:54","modified_gmt":"2026-08-15T18:06:54","slug":"pixel-to-gaussian-ultra-fast-continuous-super-resolution-with-2d-gaussian-modeling","status":"publish","type":"msr-research-item","link":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/publication\/pixel-to-gaussian-ultra-fast-continuous-super-resolution-with-2d-gaussian-modeling\/","title":{"rendered":"Pixel to Gaussian: Ultra-Fast Continuous Super-Resolution with 2D Gaussian Modeling"},"content":{"rendered":"\n\n\n<p class=\"wp-block-paragraph\">Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors using a single model, addressing the limitations of traditional SR methods constrained to fixed-scale factors (textit{e.g.}, <math><mo>\u00d7<\/mo><\/math> 2). Recent advances leveraging implicit neural representation (INR) have achieved great progress by modeling coordinate-to-pixel mappings. However, the efficiency of these methods may suffer from repeated upsampling and decoding, while their reconstruction fidelity and quality are constrained by the intrinsic representational limitations of coordinate-based functions. To address these challenges, we propose a novel ContinuousSR framework with a Pixel-to-Gaussian paradigm, which explicitly reconstructs 2D continuous HR signals from LR images using Gaussian Splatting. This approach eliminates the need for time-consuming upsampling and decoding, enabling extremely fast arbitrary-scale super-resolution. Once the Gaussian field is built in a single pass, ContinuousSR can perform arbitrary-scale rendering in just 1ms per scale. Our method introduces several key innovations. Through statistical ana&#8230;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Arbitrary-scale super-resolution (ASSR) aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs with arbitrary upsampling factors using a single model, addressing the limitations of traditional SR methods constrained to fixed-scale factors (textit{e.g.}, \u00d7 2). Recent advances leveraging implicit neural representation (INR) have achieved great progress by modeling coordinate-to-pixel mappings. However, the efficiency of these [&hellip;]<\/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":"text","value":"Long Peng","user_id":0},{"type":"text","value":"Anran Wu","user_id":0},{"type":"text","value":"Wenbo Li","user_id":0},{"type":"text","value":"Peizhe Xia","user_id":0},{"type":"text","value":"Xueyuan Dai","user_id":0},{"type":"user_nicename","value":"Xinjie Zhang","user_id":"43968"},{"type":"text","value":"Xin Di","user_id":0},{"type":"text","value":"Haoze Sun","user_id":0},{"type":"text","value":"Renjing Pei","user_id":0},{"type":"user_nicename","value":"Yang Wang","user_id":"34963"},{"type":"text","value":"Yang Cao","user_id":0},{"type":"text","value":"Zheng-Jun Zha","user_id":0}],"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"arXiv","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":"","msr_doi":"10.48550\/arXiv.2503.06617","msr_arxiv_id":"2503.06617","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":"2025-03-09","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":3,"msr_day":9,"msr_microsoftintellectualproperty":false,"msr_pub_id":"ce8c2b7b67e015feb41afa56f3cdc749308e7744","msr_publication_uploader":[{"type":"url","title":"https:\/\/arxiv.org\/abs\/2503.06617","label_id":243109,"id":false,"viewUrl":false},{"type":"url","title":"https:\/\/dblp.org\/rec\/journals\/corr\/abs-2503-06617.html","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_original_fields_of_study":[],"msr_s2_paper_id":"ce8c2b7b67e015feb41afa56f3cdc749308e7744","msr_s2_pdf_url":"","msr_citation_count_updated":"","msr_citation_count":52,"msr_influential_citations":3,"msr_reference_count":78,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[{"provider":"s2","id":"ce8c2b7b67e015feb41afa56f3cdc749308e7744"},{"provider":"doi","id":"10.48550\/arXiv.2503.06617"},{"provider":"arxiv","id":"2503.06617"},{"provider":"dblp","id":"journals\/corr\/abs-2503-06617"},{"provider":"corpusid","id":"276903151"}],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13562],"msr-publication-type":[270373],"msr-publisher":[],"msr-publication-cta":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[246691,263185],"msr-conference":[],"msr-journal":[268188],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1181186","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-computer-vision","msr-locale-en_us","msr-field-of-study-computer-science","msr-field-of-study-computer-vision-and-pattern-recognition"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2025-03-09","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":"arXiv","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":"10.48550\/arXiv.2503.06617","msr_publication_uploader":[{"type":"url","title":"https:\/\/arxiv.org\/abs\/2503.06617","label_id":243109,"id":false,"viewUrl":false},{"type":"url","title":"https:\/\/dblp.org\/rec\/journals\/corr\/abs-2503-06617.html","label_id":243109,"id":false,"viewUrl":false}],"msr_related_uploader":[],"msr_citation_count":52,"msr_citation_count_updated":"","msr_s2_paper_id":"ce8c2b7b67e015feb41afa56f3cdc749308e7744","msr_influential_citations":3,"msr_reference_count":78,"msr_arxiv_id":"2503.06617","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Long Peng","user_id":0,"rest_url":false},{"type":"text","value":"Anran Wu","user_id":0,"rest_url":false},{"type":"text","value":"Wenbo Li","user_id":0,"rest_url":false},{"type":"text","value":"Peizhe Xia","user_id":0,"rest_url":false},{"type":"text","value":"Xueyuan Dai","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Xinjie Zhang","user_id":43968,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Xinjie Zhang"},{"type":"text","value":"Xin Di","user_id":0,"rest_url":false},{"type":"text","value":"Haoze Sun","user_id":0,"rest_url":false},{"type":"text","value":"Renjing Pei","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Yang Wang","user_id":34963,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Yang Wang"},{"type":"text","value":"Yang Cao","user_id":0,"rest_url":false},{"type":"text","value":"Zheng-Jun Zha","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[199560,1012650],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"misc","related_content":[],"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1181186","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":2,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1181186\/revisions"}],"predecessor-version":[{"id":1181752,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/1181186\/revisions\/1181752"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1181186"}],"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=1181186"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1181186"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=1181186"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=1181186"},{"taxonomy":"msr-publication-cta","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-cta?post=1181186"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=1181186"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1181186"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=1181186"},{"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=1181186"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=1181186"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=1181186"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1181186"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1181186"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}