{"id":32066,"date":"2026-06-08T10:30:03","date_gmt":"2026-06-08T08:30:03","guid":{"rendered":"https:\/\/sano.science\/?p=32066"},"modified":"2026-11-17T16:35:25","modified_gmt":"2026-11-17T15:35:25","slug":"lumimotion-when-scene-motion-improves-light-2","status":"publish","type":"post","link":"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/","title":{"rendered":"LumiMotion: when scene motion improves light"},"content":{"rendered":"\n<p class=\"eplus-wrapper wp-block-paragraph\">At the Conference on&nbsp;Computer&nbsp;Vision&nbsp;and&nbsp;Pattern&nbsp;Recognition&nbsp;(CVPR) 2026 in Denver, Joanna Kaleta&nbsp;presented&nbsp;the&nbsp;highlighted&nbsp;poster \u201cLumiMotion:&nbsp;Improving&nbsp;Gaussian&nbsp;Relighting&nbsp;with&nbsp;Scene&nbsp;Dynamics\u201d,&nbsp;co\u2011authored&nbsp;with Piotr W\u00f3jcik, Kacper&nbsp;Marzol, Tomasz Trzci\u0144ski, Kacper Kania and Marek Kowalski, showing how scene dynamics can serve as an additional supervisory signal to achieve more physically grounded, flexible and&nbsp;realistic&nbsp;lighting&nbsp;in&nbsp;relighting&nbsp;pipelines&nbsp;based&nbsp;on 3D&nbsp;Gaussian&nbsp;Splatting&nbsp;\u2013 a technology increasingly used in computer graphics and&nbsp;mixed&nbsp;reality.&nbsp;<\/p>\n\n\n\n<div style=\"height:8px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n\n\n\n<p class=\"eplus-wrapper wp-block-paragraph\">CVPR&nbsp;is&nbsp;one of the&nbsp;world\u2019s&nbsp;leading&nbsp;conferences&nbsp;in&nbsp;computer&nbsp;vision&nbsp;and&nbsp;machine&nbsp;learning, and in 2026&nbsp;it&nbsp;took&nbsp;place on 3\u20137&nbsp;June&nbsp;in Denver, Colorado, with&nbsp;highlighted&nbsp;papers&nbsp;and&nbsp;posters&nbsp;representing&nbsp;a small fraction of accepted works that the community regards as particularly influential for the&nbsp;future&nbsp;of the&nbsp;field.&nbsp;<\/p>\n\n\n\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n\n\n\n<h2 id=\"h-what-nbsp-is-nbsp-lumimotion-nbsp\" class=\"wp-block-heading eplus-wrapper\">What&nbsp;is&nbsp;LumiMotion?&nbsp;<\/h2>\n\n\n\n<p class=\"eplus-wrapper wp-block-paragraph\">LumiMotion&nbsp;is a two\u2011stage inverse rendering framework whose goal is to disentangle object geometry and material from scene illumination so that lighting conditions can be realistically changed afterwards. The key idea is to treat motion as a supervisory signal that reveals the same surfaces under different lighting, helping the model understand which image variations belong to static scene&nbsp;structure&nbsp;and which are caused by changing illumination.&nbsp;<\/p>\n\n\n\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n\n\n\n<p class=\"eplus-wrapper wp-block-paragraph\">In&nbsp;practice,&nbsp;LumiMotion&nbsp;improves&nbsp;relighting&nbsp;quality&nbsp;in&nbsp;dynamic&nbsp;scenes&nbsp;where&nbsp;traditional&nbsp;3D&nbsp;Gaussian&nbsp;Splatting&nbsp;methods&nbsp;designed&nbsp;for&nbsp;static&nbsp;setups&nbsp;start to&nbsp;struggle,&nbsp;especially&nbsp;under&nbsp;complex&nbsp;lighting. By&nbsp;explicitly&nbsp;exploiting&nbsp;motion, the method achieves more consistent colors, better material appearance and&nbsp;more&nbsp;stable&nbsp;shadows&nbsp;when&nbsp;the&nbsp;direction&nbsp;or&nbsp;spectrum of&nbsp;light&nbsp;is&nbsp;modified.&nbsp;<\/p>\n\n\n\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n\n\n\n<p class=\"eplus-wrapper wp-block-paragraph\">LumiMotion is rooted in computer graphics and computer vision and its core challenge \u2014 reconstructing 3D scenes while disentangling illumination from the underlying appearance of surfaces \u2014 is highly relevant to computational medicine. This is especially important in medical imaging settings such as endoscopy, where the light source is co-located with the camera and strongly shapes what the sensor&nbsp;observes.&nbsp;Methods that make lighting more realistic, controllable, and separable from tissue appearance can support more reliable medical 3D reconstruction, more robust synthetic data generation for AI models, and better simulation and&nbsp;visualisation&nbsp;tools for training, planning, and education.&nbsp;<\/p>\n\n\n\n<div style=\"height:30px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n\n\n\n<div style=\"height:0px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n\n\n\n\t\n    \n        \n\t\t\t<a href=\"https:\/\/sanoscience.github.io\/PR-ENDO\/\" target=\"_blank\" rel= \"noopener noreferrer nofollow\" class=\"button primary \">\n\n\t\t\t\t<span>\n\t\t\t\t\tPR-ENDO: Physically Based Relightable Gaussian Splatting for Endoscopy\n\t\t\t\t<\/span>\n\n\t\t\t<\/a>\n\n        \n    \n\n\n\n<div style=\"height:30px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n\n\n\n<p class=\"eplus-wrapper wp-block-paragraph\">Joanna&nbsp;Kaleta\u2019s&nbsp;CVPR 2026 poster,&nbsp;developed&nbsp;together&nbsp;with <strong>Piotr W\u00f3jcik<\/strong>, <strong>Kacper&nbsp;Marzol<\/strong>, <strong>Tomasz Trzci\u0144ski<\/strong>, <strong>Kacper Kania<\/strong> and <strong>Marek Kowalski<\/strong>,&nbsp;illustrates&nbsp;how&nbsp;work&nbsp;at&nbsp;the&nbsp;intersection&nbsp;of&nbsp;academia&nbsp;and San&nbsp;can simultaneously advance core computer vision methods and lay technical foundations for&nbsp;future&nbsp;applications&nbsp;in&nbsp;digital&nbsp;health.&nbsp;<\/p>\n","protected":false},"excerpt":"\u2013 Joanna\u00a0Kaleta\u2019s\u00a0CVPR 2026\u00a0highlight","author":8,"featured_media":32067,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"inline_featured_image":false,"editor_plus_post_options":"{}","editor_plus_copied_stylings":"{}","_themeisle_gutenberg_block_has_review":false,"footnotes":""},"categories":[1],"tags":[],"class_list":["post-32066","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v28.8 (Yoast SEO v28.8) - https:\/\/yoast.com\/product\/yoast-seo-premium-wordpress\/ -->\n<title>LumiMotion: when scene motion improves light - Centre for Computational Personalized Medicine<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"LumiMotion: when scene motion improves light\" \/>\n<meta property=\"og:description\" content=\"\u2013 Joanna\u00a0Kaleta\u2019s\u00a0CVPR 2026\u00a0highlight\" \/>\n<meta property=\"og:url\" content=\"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/\" \/>\n<meta property=\"og:site_name\" content=\"Centre for Computational Personalized Medicine\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/sano.science\/\" \/>\n<meta property=\"article:published_time\" content=\"2026-06-08T08:30:03+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-11-17T15:35:25+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/sano.science\/wp-content\/uploads\/2026\/07\/Joanna-Kaleta-CVPR-2026.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1918\" \/>\n\t<meta property=\"og:image:height\" content=\"954\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Sano\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@sanoscience\" \/>\n<meta name=\"twitter:site\" content=\"@sanoscience\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sano\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/sano.science\\\/lumimotion-when-scene-motion-improves-light-2\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/sano.science\\\/lumimotion-when-scene-motion-improves-light-2\\\/\"},\"author\":{\"name\":\"Sano\",\"@id\":\"https:\\\/\\\/sano.science\\\/#\\\/schema\\\/person\\\/584b688db91327a7862fe87518e38c51\"},\"headline\":\"LumiMotion: when scene motion improves light\",\"datePublished\":\"2026-06-08T08:30:03+00:00\",\"dateModified\":\"2026-11-17T15:35:25+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/sano.science\\\/lumimotion-when-scene-motion-improves-light-2\\\/\"},\"wordCount\":532,\"publisher\":{\"@id\":\"https:\\\/\\\/sano.science\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/sano.science\\\/lumimotion-when-scene-motion-improves-light-2\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/sano.science\\\/wp-content\\\/uploads\\\/2026\\\/07\\\/Joanna-Kaleta-CVPR-2026.jpg\",\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/sano.science\\\/lumimotion-when-scene-motion-improves-light-2\\\/\",\"url\":\"https:\\\/\\\/sano.science\\\/lumimotion-when-scene-motion-improves-light-2\\\/\",\"name\":\"LumiMotion: when scene motion improves light - Centre for Computational Personalized Medicine\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/sano.science\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/sano.science\\\/lumimotion-when-scene-motion-improves-light-2\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/sano.science\\\/lumimotion-when-scene-motion-improves-light-2\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/sano.science\\\/wp-content\\\/uploads\\\/2026\\\/07\\\/Joanna-Kaleta-CVPR-2026.jpg\",\"datePublished\":\"2026-06-08T08:30:03+00:00\",\"dateModified\":\"2026-11-17T15:35:25+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/sano.science\\\/lumimotion-when-scene-motion-improves-light-2\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/sano.science\\\/lumimotion-when-scene-motion-improves-light-2\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/sano.science\\\/lumimotion-when-scene-motion-improves-light-2\\\/#primaryimage\",\"url\":\"https:\\\/\\\/sano.science\\\/wp-content\\\/uploads\\\/2026\\\/07\\\/Joanna-Kaleta-CVPR-2026.jpg\",\"contentUrl\":\"https:\\\/\\\/sano.science\\\/wp-content\\\/uploads\\\/2026\\\/07\\\/Joanna-Kaleta-CVPR-2026.jpg\",\"width\":1918,\"height\":954,\"caption\":\"Screenshot\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/sano.science\\\/lumimotion-when-scene-motion-improves-light-2\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/sano.science\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"LumiMotion: when scene motion improves light\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/sano.science\\\/#website\",\"url\":\"https:\\\/\\\/sano.science\\\/\",\"name\":\"Centre for Computational Personalized Medicine\",\"description\":\"Sano \u2013 Centre for Computational Medicine\",\"publisher\":{\"@id\":\"https:\\\/\\\/sano.science\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/sano.science\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/sano.science\\\/#organization\",\"name\":\"Sano \u2013 Centre for Computational Medicine\",\"alternateName\":\"Sano\",\"url\":\"https:\\\/\\\/sano.science\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/sano.science\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/sano.science\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/logo_sano_podstawowe.png\",\"contentUrl\":\"https:\\\/\\\/sano.science\\\/wp-content\\\/uploads\\\/2024\\\/05\\\/logo_sano_podstawowe.png\",\"width\":700,\"height\":265,\"caption\":\"Sano \u2013 Centre for Computational Medicine\"},\"image\":{\"@id\":\"https:\\\/\\\/sano.science\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/www.facebook.com\\\/sano.science\\\/\",\"https:\\\/\\\/x.com\\\/sanoscience\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/sanoscience\\\/\",\"https:\\\/\\\/www.youtube.com\\\/channel\\\/UCDZ_8TcjMWUG2ZcgKKgfpwQ\",\"https:\\\/\\\/bsky.app\\\/profile\\\/sanoscience.bsky.social\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/sano.science\\\/#\\\/schema\\\/person\\\/584b688db91327a7862fe87518e38c51\",\"name\":\"Sano\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/3349c3947cb21b81e9745a6442fe4ec43961bb077198eb416cbdc66ec45ea97c?s=96&d=mm&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/3349c3947cb21b81e9745a6442fe4ec43961bb077198eb416cbdc66ec45ea97c?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/3349c3947cb21b81e9745a6442fe4ec43961bb077198eb416cbdc66ec45ea97c?s=96&d=mm&r=g\",\"caption\":\"Sano\"},\"url\":\"https:\\\/\\\/sano.science\\\/author\\\/s15to\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"LumiMotion: when scene motion improves light - Centre for Computational Personalized Medicine","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/","og_locale":"en_US","og_type":"article","og_title":"LumiMotion: when scene motion improves light","og_description":"\u2013 Joanna\u00a0Kaleta\u2019s\u00a0CVPR 2026\u00a0highlight","og_url":"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/","og_site_name":"Centre for Computational Personalized Medicine","article_publisher":"https:\/\/www.facebook.com\/sano.science\/","article_published_time":"2026-06-08T08:30:03+00:00","article_modified_time":"2026-11-17T15:35:25+00:00","og_image":[{"width":1918,"height":954,"url":"https:\/\/sano.science\/wp-content\/uploads\/2026\/07\/Joanna-Kaleta-CVPR-2026.jpg","type":"image\/jpeg"}],"author":"Sano","twitter_card":"summary_large_image","twitter_creator":"@sanoscience","twitter_site":"@sanoscience","twitter_misc":{"Written by":"Sano","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/#article","isPartOf":{"@id":"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/"},"author":{"name":"Sano","@id":"https:\/\/sano.science\/#\/schema\/person\/584b688db91327a7862fe87518e38c51"},"headline":"LumiMotion: when scene motion improves light","datePublished":"2026-06-08T08:30:03+00:00","dateModified":"2026-11-17T15:35:25+00:00","mainEntityOfPage":{"@id":"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/"},"wordCount":532,"publisher":{"@id":"https:\/\/sano.science\/#organization"},"image":{"@id":"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/#primaryimage"},"thumbnailUrl":"https:\/\/sano.science\/wp-content\/uploads\/2026\/07\/Joanna-Kaleta-CVPR-2026.jpg","inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/","url":"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/","name":"LumiMotion: when scene motion improves light - Centre for Computational Personalized Medicine","isPartOf":{"@id":"https:\/\/sano.science\/#website"},"primaryImageOfPage":{"@id":"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/#primaryimage"},"image":{"@id":"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/#primaryimage"},"thumbnailUrl":"https:\/\/sano.science\/wp-content\/uploads\/2026\/07\/Joanna-Kaleta-CVPR-2026.jpg","datePublished":"2026-06-08T08:30:03+00:00","dateModified":"2026-11-17T15:35:25+00:00","breadcrumb":{"@id":"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/#primaryimage","url":"https:\/\/sano.science\/wp-content\/uploads\/2026\/07\/Joanna-Kaleta-CVPR-2026.jpg","contentUrl":"https:\/\/sano.science\/wp-content\/uploads\/2026\/07\/Joanna-Kaleta-CVPR-2026.jpg","width":1918,"height":954,"caption":"Screenshot"},{"@type":"BreadcrumbList","@id":"https:\/\/sano.science\/lumimotion-when-scene-motion-improves-light-2\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/sano.science\/"},{"@type":"ListItem","position":2,"name":"LumiMotion: when scene motion improves light"}]},{"@type":"WebSite","@id":"https:\/\/sano.science\/#website","url":"https:\/\/sano.science\/","name":"Centre for Computational Personalized Medicine","description":"Sano \u2013 Centre for Computational Medicine","publisher":{"@id":"https:\/\/sano.science\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/sano.science\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/sano.science\/#organization","name":"Sano \u2013 Centre for Computational Medicine","alternateName":"Sano","url":"https:\/\/sano.science\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/sano.science\/#\/schema\/logo\/image\/","url":"https:\/\/sano.science\/wp-content\/uploads\/2024\/05\/logo_sano_podstawowe.png","contentUrl":"https:\/\/sano.science\/wp-content\/uploads\/2024\/05\/logo_sano_podstawowe.png","width":700,"height":265,"caption":"Sano \u2013 Centre for Computational Medicine"},"image":{"@id":"https:\/\/sano.science\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/sano.science\/","https:\/\/x.com\/sanoscience","https:\/\/www.linkedin.com\/company\/sanoscience\/","https:\/\/www.youtube.com\/channel\/UCDZ_8TcjMWUG2ZcgKKgfpwQ","https:\/\/bsky.app\/profile\/sanoscience.bsky.social"]},{"@type":"Person","@id":"https:\/\/sano.science\/#\/schema\/person\/584b688db91327a7862fe87518e38c51","name":"Sano","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/3349c3947cb21b81e9745a6442fe4ec43961bb077198eb416cbdc66ec45ea97c?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/3349c3947cb21b81e9745a6442fe4ec43961bb077198eb416cbdc66ec45ea97c?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/3349c3947cb21b81e9745a6442fe4ec43961bb077198eb416cbdc66ec45ea97c?s=96&d=mm&r=g","caption":"Sano"},"url":"https:\/\/sano.science\/author\/s15to\/"}]}},"acf":[],"gutenberg_blocks":[{"blockName":"custom-styles","attrs":{"styles":""}},{"blockName":"core\/paragraph","attrs":{"epAnimationGeneratedClass":"edplus_anim-Z0YQ9R","epGeneratedClass":"eplus-wrapper"},"innerBlocks":[],"innerHTML":"\n<p class=\" eplus-wrapper\">At the Conference on&nbsp;Computer&nbsp;Vision&nbsp;and&nbsp;Pattern&nbsp;Recognition&nbsp;(CVPR) 2026 in Denver, Joanna Kaleta&nbsp;presented&nbsp;the&nbsp;highlighted&nbsp;poster \u201cLumiMotion:&nbsp;Improving&nbsp;Gaussian&nbsp;Relighting&nbsp;with&nbsp;Scene&nbsp;Dynamics\u201d,&nbsp;co\u2011authored&nbsp;with Piotr W\u00f3jcik, Kacper&nbsp;Marzol, Tomasz Trzci\u0144ski, Kacper Kania and Marek Kowalski, showing how scene dynamics can serve as an additional supervisory signal to achieve more physically grounded, flexible and&nbsp;realistic&nbsp;lighting&nbsp;in&nbsp;relighting&nbsp;pipelines&nbsp;based&nbsp;on 3D&nbsp;Gaussian&nbsp;Splatting&nbsp;\u2013 a technology increasingly used in computer graphics and&nbsp;mixed&nbsp;reality.&nbsp;<\/p>\n","innerContent":["\n<p class=\" eplus-wrapper\">At the Conference on&nbsp;Computer&nbsp;Vision&nbsp;and&nbsp;Pattern&nbsp;Recognition&nbsp;(CVPR) 2026 in Denver, Joanna Kaleta&nbsp;presented&nbsp;the&nbsp;highlighted&nbsp;poster \u201cLumiMotion:&nbsp;Improving&nbsp;Gaussian&nbsp;Relighting&nbsp;with&nbsp;Scene&nbsp;Dynamics\u201d,&nbsp;co\u2011authored&nbsp;with Piotr W\u00f3jcik, Kacper&nbsp;Marzol, Tomasz Trzci\u0144ski, Kacper Kania and Marek Kowalski, showing how scene dynamics can serve as an additional supervisory signal to achieve more physically grounded, flexible and&nbsp;realistic&nbsp;lighting&nbsp;in&nbsp;relighting&nbsp;pipelines&nbsp;based&nbsp;on 3D&nbsp;Gaussian&nbsp;Splatting&nbsp;\u2013 a technology increasingly used in computer graphics and&nbsp;mixed&nbsp;reality.&nbsp;<\/p>\n"]},{"blockName":"core\/spacer","attrs":{"height":"8px","epAnimationGeneratedClass":"edplus_anim-6LvOyF","epGeneratedClass":"eplus-wrapper"},"innerBlocks":[],"innerHTML":"\n<div style=\"height:8px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n","innerContent":["\n<div style=\"height:8px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n"]},{"blockName":"core\/paragraph","attrs":{"epAnimationGeneratedClass":"edplus_anim-JLx7Th","epGeneratedClass":"eplus-wrapper"},"innerBlocks":[],"innerHTML":"\n<p class=\" eplus-wrapper\">CVPR&nbsp;is&nbsp;one of the&nbsp;world\u2019s&nbsp;leading&nbsp;conferences&nbsp;in&nbsp;computer&nbsp;vision&nbsp;and&nbsp;machine&nbsp;learning, and in 2026&nbsp;it&nbsp;took&nbsp;place on 3\u20137&nbsp;June&nbsp;in Denver, Colorado, with&nbsp;highlighted&nbsp;papers&nbsp;and&nbsp;posters&nbsp;representing&nbsp;a small fraction of accepted works that the community regards as particularly influential for the&nbsp;future&nbsp;of the&nbsp;field.&nbsp;<\/p>\n","innerContent":["\n<p class=\" eplus-wrapper\">CVPR&nbsp;is&nbsp;one of the&nbsp;world\u2019s&nbsp;leading&nbsp;conferences&nbsp;in&nbsp;computer&nbsp;vision&nbsp;and&nbsp;machine&nbsp;learning, and in 2026&nbsp;it&nbsp;took&nbsp;place on 3\u20137&nbsp;June&nbsp;in Denver, Colorado, with&nbsp;highlighted&nbsp;papers&nbsp;and&nbsp;posters&nbsp;representing&nbsp;a small fraction of accepted works that the community regards as particularly influential for the&nbsp;future&nbsp;of the&nbsp;field.&nbsp;<\/p>\n"]},{"blockName":"core\/spacer","attrs":{"height":"10px","epAnimationGeneratedClass":"edplus_anim-yfYHku","epGeneratedClass":"eplus-wrapper"},"innerBlocks":[],"innerHTML":"\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n","innerContent":["\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n"]},{"blockName":"core\/heading","attrs":{"anchor":"h-what-nbsp-is-nbsp-lumimotion-nbsp","epAnimationGeneratedClass":"edplus_anim-3fZqGU","epGeneratedClass":"eplus-wrapper"},"innerBlocks":[],"innerHTML":"\n<h2 id=\"h-what-nbsp-is-nbsp-lumimotion-nbsp\" class=\"wp-block-heading eplus-wrapper\">What&nbsp;is&nbsp;LumiMotion?&nbsp;<\/h2>\n","innerContent":["\n<h2 id=\"h-what-nbsp-is-nbsp-lumimotion-nbsp\" class=\"wp-block-heading eplus-wrapper\">What&nbsp;is&nbsp;LumiMotion?&nbsp;<\/h2>\n"]},{"blockName":"core\/paragraph","attrs":{"epAnimationGeneratedClass":"edplus_anim-bPTfXz","epGeneratedClass":"eplus-wrapper"},"innerBlocks":[],"innerHTML":"\n<p class=\" eplus-wrapper\">LumiMotion&nbsp;is a two\u2011stage inverse rendering framework whose goal is to disentangle object geometry and material from scene illumination so that lighting conditions can be realistically changed afterwards. The key idea is to treat motion as a supervisory signal that reveals the same surfaces under different lighting, helping the model understand which image variations belong to static scene&nbsp;structure&nbsp;and which are caused by changing illumination.&nbsp;<\/p>\n","innerContent":["\n<p class=\" eplus-wrapper\">LumiMotion&nbsp;is a two\u2011stage inverse rendering framework whose goal is to disentangle object geometry and material from scene illumination so that lighting conditions can be realistically changed afterwards. The key idea is to treat motion as a supervisory signal that reveals the same surfaces under different lighting, helping the model understand which image variations belong to static scene&nbsp;structure&nbsp;and which are caused by changing illumination.&nbsp;<\/p>\n"]},{"blockName":"core\/spacer","attrs":{"height":"10px","epAnimationGeneratedClass":"edplus_anim-xRHqJ3","epGeneratedClass":"eplus-wrapper"},"innerBlocks":[],"innerHTML":"\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n","innerContent":["\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n"]},{"blockName":"core\/paragraph","attrs":{"epAnimationGeneratedClass":"edplus_anim-4jLa2m","epGeneratedClass":"eplus-wrapper"},"innerBlocks":[],"innerHTML":"\n<p class=\" eplus-wrapper\">In&nbsp;practice,&nbsp;LumiMotion&nbsp;improves&nbsp;relighting&nbsp;quality&nbsp;in&nbsp;dynamic&nbsp;scenes&nbsp;where&nbsp;traditional&nbsp;3D&nbsp;Gaussian&nbsp;Splatting&nbsp;methods&nbsp;designed&nbsp;for&nbsp;static&nbsp;setups&nbsp;start to&nbsp;struggle,&nbsp;especially&nbsp;under&nbsp;complex&nbsp;lighting. By&nbsp;explicitly&nbsp;exploiting&nbsp;motion, the method achieves more consistent colors, better material appearance and&nbsp;more&nbsp;stable&nbsp;shadows&nbsp;when&nbsp;the&nbsp;direction&nbsp;or&nbsp;spectrum of&nbsp;light&nbsp;is&nbsp;modified.&nbsp;<\/p>\n","innerContent":["\n<p class=\" eplus-wrapper\">In&nbsp;practice,&nbsp;LumiMotion&nbsp;improves&nbsp;relighting&nbsp;quality&nbsp;in&nbsp;dynamic&nbsp;scenes&nbsp;where&nbsp;traditional&nbsp;3D&nbsp;Gaussian&nbsp;Splatting&nbsp;methods&nbsp;designed&nbsp;for&nbsp;static&nbsp;setups&nbsp;start to&nbsp;struggle,&nbsp;especially&nbsp;under&nbsp;complex&nbsp;lighting. By&nbsp;explicitly&nbsp;exploiting&nbsp;motion, the method achieves more consistent colors, better material appearance and&nbsp;more&nbsp;stable&nbsp;shadows&nbsp;when&nbsp;the&nbsp;direction&nbsp;or&nbsp;spectrum of&nbsp;light&nbsp;is&nbsp;modified.&nbsp;<\/p>\n"]},{"blockName":"core\/spacer","attrs":{"height":"10px","epAnimationGeneratedClass":"edplus_anim-rldFC2","epGeneratedClass":"eplus-wrapper"},"innerBlocks":[],"innerHTML":"\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n","innerContent":["\n<div style=\"height:10px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n"]},{"blockName":"core\/paragraph","attrs":{"epAnimationGeneratedClass":"edplus_anim-9TJ06o","epGeneratedClass":"eplus-wrapper"},"innerBlocks":[],"innerHTML":"\n<p class=\" eplus-wrapper\">LumiMotion is rooted in computer graphics and computer vision and its core challenge \u2014 reconstructing 3D scenes while disentangling illumination from the underlying appearance of surfaces \u2014 is highly relevant to computational medicine. This is especially important in medical imaging settings such as endoscopy, where the light source is co-located with the camera and strongly shapes what the sensor&nbsp;observes.&nbsp;Methods that make lighting more realistic, controllable, and separable from tissue appearance can support more reliable medical 3D reconstruction, more robust synthetic data generation for AI models, and better simulation and&nbsp;visualisation&nbsp;tools for training, planning, and education.&nbsp;<\/p>\n","innerContent":["\n<p class=\" eplus-wrapper\">LumiMotion is rooted in computer graphics and computer vision and its core challenge \u2014 reconstructing 3D scenes while disentangling illumination from the underlying appearance of surfaces \u2014 is highly relevant to computational medicine. This is especially important in medical imaging settings such as endoscopy, where the light source is co-located with the camera and strongly shapes what the sensor&nbsp;observes.&nbsp;Methods that make lighting more realistic, controllable, and separable from tissue appearance can support more reliable medical 3D reconstruction, more robust synthetic data generation for AI models, and better simulation and&nbsp;visualisation&nbsp;tools for training, planning, and education.&nbsp;<\/p>\n"]},{"blockName":"core\/spacer","attrs":{"height":"30px","epAnimationGeneratedClass":"edplus_anim-MGYw0q","epGeneratedClass":"eplus-wrapper"},"innerBlocks":[],"innerHTML":"\n<div style=\"height:30px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n","innerContent":["\n<div style=\"height:30px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n"]},{"blockName":"core\/spacer","attrs":{"height":"0px","epAnimationGeneratedClass":"edplus_anim-PsDtKc","epGeneratedClass":"eplus-wrapper"},"innerBlocks":[],"innerHTML":"\n<div style=\"height:0px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n","innerContent":["\n<div style=\"height:0px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n"]},{"blockName":"acf\/button","attrs":{"title":"PR-ENDO: Physically Based Relightable Gaussian Splatting for Endoscopy","button_type":"link","url":"https:\/\/sanoscience.github.io\/PR-ENDO\/","button_style":"primary","target":"_blank","button_extra_classes":""},"innerBlocks":[],"innerHTML":"","innerContent":[]},{"blockName":"core\/spacer","attrs":{"height":"30px","epAnimationGeneratedClass":"edplus_anim-PsDtKc","epGeneratedClass":"eplus-wrapper"},"innerBlocks":[],"innerHTML":"\n<div style=\"height:30px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n","innerContent":["\n<div style=\"height:30px\" aria-hidden=\"true\" class=\"wp-block-spacer eplus-wrapper\"><\/div>\n"]},{"blockName":"core\/paragraph","attrs":{"epAnimationGeneratedClass":"edplus_anim-FnHKY5","epGeneratedClass":"eplus-wrapper"},"innerBlocks":[],"innerHTML":"\n<p class=\" eplus-wrapper\">Joanna&nbsp;Kaleta\u2019s&nbsp;CVPR 2026 poster,&nbsp;developed&nbsp;together&nbsp;with <strong>Piotr W\u00f3jcik<\/strong>, <strong>Kacper&nbsp;Marzol<\/strong>, <strong>Tomasz Trzci\u0144ski<\/strong>, <strong>Kacper Kania<\/strong> and <strong>Marek Kowalski<\/strong>,&nbsp;illustrates&nbsp;how&nbsp;work&nbsp;at&nbsp;the&nbsp;intersection&nbsp;of&nbsp;academia&nbsp;and San&nbsp;can simultaneously advance core computer vision methods and lay technical foundations for&nbsp;future&nbsp;applications&nbsp;in&nbsp;digital&nbsp;health.&nbsp;<\/p>\n","innerContent":["\n<p class=\" eplus-wrapper\">Joanna&nbsp;Kaleta\u2019s&nbsp;CVPR 2026 poster,&nbsp;developed&nbsp;together&nbsp;with <strong>Piotr W\u00f3jcik<\/strong>, <strong>Kacper&nbsp;Marzol<\/strong>, <strong>Tomasz Trzci\u0144ski<\/strong>, <strong>Kacper Kania<\/strong> and <strong>Marek Kowalski<\/strong>,&nbsp;illustrates&nbsp;how&nbsp;work&nbsp;at&nbsp;the&nbsp;intersection&nbsp;of&nbsp;academia&nbsp;and San&nbsp;can simultaneously advance core computer vision methods and lay technical foundations for&nbsp;future&nbsp;applications&nbsp;in&nbsp;digital&nbsp;health.&nbsp;<\/p>\n"]}],"meta_data":{"has_thumbnail_pattern":false,"share_on_social_media":{"has_social_media":false}},"featured_image":{"url":"https:\/\/sano.science\/wp-content\/uploads\/2026\/07\/Joanna-Kaleta-CVPR-2026-1024x509.jpg"},"main_category":{"name":"Uncategorized"},"prev_page":{"slug":"malawski-at-the-us-poland-science-and-technology-symposium-2026"},"next_page":{"slug":"lumimotion-when-scene-motion-improves-light"},"_links":{"self":[{"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/posts\/32066","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/users\/8"}],"replies":[{"embeddable":true,"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/comments?post=32066"}],"version-history":[{"count":5,"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/posts\/32066\/revisions"}],"predecessor-version":[{"id":33328,"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/posts\/32066\/revisions\/33328"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/media\/32067"}],"wp:attachment":[{"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/media?parent=32066"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/categories?post=32066"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/sano.science\/index.php\/wp-json\/wp\/v2\/tags?post=32066"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}