{"id":23669,"date":"2026-09-18T09:31:35","date_gmt":"2026-09-18T01:31:35","guid":{"rendered":"https:\/\/cde.nus.edu.sg\/ece\/?post_type=nus-news&#038;p=23669"},"modified":"2026-09-18T09:47:46","modified_gmt":"2026-09-18T01:47:46","slug":"nus-ece-research-selected-as-eccv-2026-award-candidate","status":"publish","type":"nus-news","link":"https:\/\/cde.nus.edu.sg\/ece\/news\/nus-ece-research-selected-as-eccv-2026-award-candidate\/","title":{"rendered":"NUS ECE Research Selected as ECCV 2026 Award Candidate"},"content":{"rendered":"<p class=\"isSelectedEnd\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-23671 \" src=\"https:\/\/cde.nus.edu.sg\/ece\/wp-content\/uploads\/sites\/3\/2026\/09\/Zhang-Shihua.jpg\" alt=\"\" width=\"378\" height=\"396\" srcset=\"https:\/\/cde.nus.edu.sg\/ece\/wp-content\/uploads\/sites\/3\/2026\/09\/Zhang-Shihua.jpg 346w, https:\/\/cde.nus.edu.sg\/ece\/wp-content\/uploads\/sites\/3\/2026\/09\/Zhang-Shihua-287x300.jpg 287w\" sizes=\"auto, (max-width: 378px) 100vw, 378px\" \/><\/p>\n<p class=\"isSelectedEnd\">Vision-language models (VLMs) have made significant advances in understanding images and videos, but accurately reasoning about spatial relationships remains challenging. In particular, models may rely heavily on visual appearance while underutilising important geometric information.<\/p>\n<p class=\"isSelectedEnd\">The paper introduces GeoSR, a framework designed to encourage VLMs to make better use of geometric information for spatial reasoning in both static images and dynamic videos. GeoSR incorporates two key techniques. Geometry-Unleashing Masking strategically masks portions of 2D visual information during training, encouraging the model to rely more on geometric cues. Geometry-Guided Fusion then uses a learned gating mechanism to adaptively strengthen geometric information where it is most relevant. Through these approaches, GeoSR enables VLMs to more effectively leverage 3D geometric cues when reasoning about spatial relationships. Experiments on static and dynamic spatial reasoning benchmarks demonstrated consistent improvements over existing geometry-aware approaches, establishing new state-of-the-art performance on the reported benchmarks.<\/p>\n<p>The research highlights how incorporating geometric understanding can strengthen the ability of AI systems to reason about the physical world, with potential applications in areas such as embodied AI, robotics and intelligent systems.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"alignnone wp-image-23670 size-full\" src=\"https:\/\/cde.nus.edu.sg\/ece\/wp-content\/uploads\/sites\/3\/2026\/09\/Zhang-Shihua-1.jpg.png\" alt=\"\" width=\"554\" height=\"415\" srcset=\"https:\/\/cde.nus.edu.sg\/ece\/wp-content\/uploads\/sites\/3\/2026\/09\/Zhang-Shihua-1.jpg.png 554w, https:\/\/cde.nus.edu.sg\/ece\/wp-content\/uploads\/sites\/3\/2026\/09\/Zhang-Shihua-1.jpg-300x225.png 300w\" sizes=\"auto, (max-width: 554px) 100vw, 554px\" \/><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Congratulations to ECE PhD student Mr. Zhang Shihua and his co-authors from the Department of Electrical and Computer Engineering (ECE), National University of Singapore (NUS), whose paper, \u201cMake Geometry Matter for Spatial Reasoning,\u201d was selected as one of 10 Award Candidates at the 19th European Conference on Computer Vision (ECCV 2026). The paper was also accepted as an ECCV 2026 Long Oral Presentation. Mr. Zhang Shihua is supervised by Associate Professor Wang Xinchao. The paper was co-authored by Shihua Zhang, Qiuhong Shen, Shizun Wang, Tianbo Pan and Xinchao Wang.<\/p>\n","protected":false},"author":8,"featured_media":23671,"parent":0,"menu_order":0,"template":"","meta":{"_acf_changed":false,"rs_blank_template":"","rs_page_bg_color":"","slide_template_v7":"","site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"default","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"set","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"news_category":[37,47,49],"class_list":["post-23669","nus-news","type-nus-news","status-publish","has-post-thumbnail","hentry","news_category-ece","news_category-awards-achievements","news_category-research-impact"],"acf":[],"_links":{"self":[{"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/news\/23669","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/news"}],"about":[{"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/types\/nus-news"}],"author":[{"embeddable":true,"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/users\/8"}],"version-history":[{"count":4,"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/news\/23669\/revisions"}],"predecessor-version":[{"id":23675,"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/news\/23669\/revisions\/23675"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/media\/23671"}],"wp:attachment":[{"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/media?parent=23669"}],"wp:term":[{"taxonomy":"news_category","embeddable":true,"href":"https:\/\/cde.nus.edu.sg\/ece\/wp-json\/wp\/v2\/news_category?post=23669"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}