{"id":3127,"date":"2026-05-05T11:01:08","date_gmt":"2026-05-05T11:01:08","guid":{"rendered":"https:\/\/www.europesays.com\/korea\/3127\/"},"modified":"2026-05-05T11:01:08","modified_gmt":"2026-05-05T11:01:08","slug":"robotics-chatgpt-moment-naver-leads-spatial-intelligence-race","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/korea\/3127\/","title":{"rendered":"Robotics’ ChatGPT Moment: Naver Leads Spatial Intelligence Race"},"content":{"rendered":"

\"JeromeJerome Revaud, Naver Labs Europe developer. Seongnam \u2014 Oh Seung-hyun
\nJerome Revaud, Naver Labs Europe developer. Seongnam \u2014 Oh Seung-hyun, April 24, 2026<\/p>\n

Upload a single photo of an office interior, and it is instantly transformed into a three-dimensional space. The structures and objects throughout the room appear vividly on a 3D screen, as if the viewer had stepped inside to look around. This magical moment is created by DUSt3R, a 3D vision foundation model developed by Naver Labs, the research and development subsidiary of Naver (035420.KS).<\/p>\n

Jerome Revaud, the researcher at Naver Labs Europe who led DUSt3R’s development, compared the process to the “ChatGPT moment” that drove AI into the mainstream. “Introducing foundation models to the robotics field is truly a game-changer,” he said in an interview with Seoul Economic Daily on Thursday at Naver’s 1784 headquarters in Seongnam, Gyeonggi Province.<\/p>\n

Revaud, an expert who worked at France’s National Institute for Research in Digital Science and Technology before joining the Xerox Research Centre Europe, has been leading the 3D vision foundation model development project since Naver acquired the Xerox Research Centre Europe in 2017.<\/p>\n

For a robot to move smoothly in a real environment, it needs a kind of “eye” that can comprehensively perceive visual information such as direction and distance, beyond simply identifying objects in front of it. DUSt3R solves this challenge by applying deep learning technology to 3D vision, enabling AI to learn physical elements on its own. As a result, the model can grasp spatial information and generate 3D data from just a few photos, while also extracting geometric information such as depth and camera position.<\/p>\n

\"null<\/p>\n

“In the past, natural language processing (NLP) was divided into various fields such as translation, sentiment analysis, and text summarization. But with the emergence of ChatGPT, a text foundation model, an innovation occurred in which a single model handles all these tasks with superior performance,” Revaud said. “The emergence of DUSt3R has similarly opened the way to solve all existing 3D vision tasks with a single model.”<\/p>\n

After developing DUSt3R, Naver Labs chose to release it as open source rather than commercialize it. The decision reflects the judgment that expanding the related research ecosystem takes priority, allowing 3D vision foundation models to advance rapidly. “By opening up the technology, we can harness academic research capabilities from around the world, which will lead to faster improvements of the model,” Revaud explained. “Furthermore, it will bring tremendous promotional effects to the Naver brand and yield greater gains in the long run.”<\/p>\n

Indeed, DUSt3R has recorded 1,418 paper citations in just two years since its release, and global Big Tech companies including Meta, Google, and Nvidia are conducting follow-up research based on it, establishing the model as a clear “game changer” in the spatial intelligence field.<\/p>\n

Naver is currently pursuing the commercialization of various services based on DUSt3R technology. Representative examples include enhancing the “Street View” function of Naver Map and implementing interior photos of real estate listings on Naver Pay as augmented reality (AR). Going forward, the applications are expected to be limitless, from producing 3D interior renderings to recreating historical sites that exist only in photos as three-dimensional content.<\/p>\n

The ultimate goal is to establish this technology as a core foundational technology that helps robots operate smoothly in actual industrial sites. “Robots are more than large language models (LLMs). They must integrate diverse sensor data such as vision and voice, and encompass physical elements such as collaboration and interaction among multiple robots,” Revaud stressed. “This is precisely the core challenge that Naver Labs Europe is focusing on.”<\/p>\n

\"null<\/p>\n","protected":false},"excerpt":{"rendered":"Jerome Revaud, Naver Labs Europe developer. Seongnam \u2014 Oh Seung-hyun Jerome Revaud, Naver Labs Europe developer. Seongnam \u2014…\n","protected":false},"author":2,"featured_media":3128,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[623],"tags":[2759,2758,2760,657,2757,2763,2762,1437,2761],"class_list":["post-3127","post","type-post","status-publish","format-standard","has-post-thumbnail","category-naver","tag-3d-vision-foundation-model","tag-dust3r","tag-jerome-revaud","tag-naver","tag-naver-labs","tag-naver-map-street-view","tag-open-source","tag-robotics-ai","tag-spatial-intelligence"],"_links":{"self":[{"href":"https:\/\/www.europesays.com\/korea\/wp-json\/wp\/v2\/posts\/3127","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/korea\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/korea\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/korea\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/korea\/wp-json\/wp\/v2\/comments?post=3127"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/korea\/wp-json\/wp\/v2\/posts\/3127\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/korea\/wp-json\/wp\/v2\/media\/3128"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/korea\/wp-json\/wp\/v2\/media?parent=3127"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/korea\/wp-json\/wp\/v2\/categories?post=3127"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/korea\/wp-json\/wp\/v2\/tags?post=3127"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}