135565 20260217205525.0 doi 10.1111/cgf.15037 sideral 138724 ART-2024-138724 eng Guerrero-Viu, Julia Universidad de Zaragoza (orcid)0000-0002-2077-683X Predicting Perceived Gloss: Do Weak Labels Suffice? 2024 Access copy available to the general public Unrestricted Estimating perceptual attributes of materials directly from images is a challenging task due to their complex, not fully‐understood interactions with external factors, such as geometry and lighting. Supervised deep learning models have recently been shown to outperform traditional approaches, but rely on large datasets of human‐annotated images for accurate perception predictions. Obtaining reliable annotations is a costly endeavor, aggravated by the limited ability of these models to generalise to different aspects of appearance. In this work, we show how a much smaller set of human annotations (“strong labels”) can be effectively augmented with automatically derived “weak labels” in the context of learning a low‐dimensional image‐computable gloss metric. We evaluate three alternative weak labels for predicting human gloss perception from limited annotated data. Incorporating weak labels enhances our gloss prediction beyond the current state of the art. Moreover, it enables a substantial reduction in human annotation costs without sacrificing accuracy, whether working with rendered images or real photographs. info:eu-repo/grantAgreement/ES/DGA-CUS/702-2022 info:eu-repo/grantAgreement/EC/HORIZON EUROPE/101098225/EU/Seeing Stuff: Perceiving Materials and their Properties/STUFF info:eu-repo/grantAgreement/EC/H2020/956585/EU/Predictive Rendering In Manufacture and Engineering/PRIME This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No H2020 956585-PRIME info:eu-repo/grantAgreement/ES/MCIU/FPU20-02340 info:eu-repo/grantAgreement/ES/MICINN/PID2022-141766OB-I00 info:eu-repo/semantics/openAccess by-nc https://creativecommons.org/licenses/by-nc/4.0/deed.es 2.9 2024 COMPUTER SCIENCE, SOFTWARE ENGINEERING 49 / 129 = 0.38 2024 Q2 T2 0.788 2024 Computer Graphics and Computer-Aided Design 2024 Q1 Computer Networks and Communications 2024 Q2 6.0 2024 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Subias, J. Daniel Universidad de Zaragoza (orcid)0000-0002-5480-7462 Serrano, Ana Universidad de Zaragoza (orcid)0000-0002-7796-3177 Storrs, Katherine R. Fleming, Roland W. Masia, Belen Universidad de Zaragoza (orcid)0000-0003-0060-7278 Gutierrez, Diego Universidad de Zaragoza (orcid)0000-0002-7503-7022 5007 570 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Lenguajes y Sistemas Inf. 43, 2 (2024), e15037 [13 pp.] Comput. graph. forum Computer Graphics Forum 0167-7055 2894923 http://zaguan.unizar.es/record/135565/files/texto_completo.pdf Versión publicada 2162813 http://zaguan.unizar.es/record/135565/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:135565 articulos driver 2026-02-17-20:30:25 ARTICLE