Image-Driven Furniture Style for Interactive 3D Scene Modeling

dc.contributor.authorWeiss, Tomeren_US
dc.contributor.authorYildiz, Ilkayen_US
dc.contributor.authorAgarwal, Nitinen_US
dc.contributor.authorAtaer-Cansizoglu, Esraen_US
dc.contributor.authorChoi, Jae-Wooen_US
dc.contributor.editorEisemann, Elmar and Jacobson, Alec and Zhang, Fang-Lueen_US
dc.date.accessioned2020-10-29T18:49:55Z
dc.date.available2020-10-29T18:49:55Z
dc.date.issued2020
dc.description.abstractCreating realistic styled spaces is a complex task, which involves design know-how for what furniture pieces go well together. Interior style follows abstract rules involving color, geometry and other visual elements. Following such rules, users manually select similar-style items from large repositories of 3D furniture models, a process which is both laborious and time-consuming. We propose a method for fast-tracking style-similarity tasks, by learning a furniture's style-compatibility from interior scene images. Such images contain more style information than images depicting single furniture. To understand style, we train a deep learning network on a classification task. Based on image embeddings extracted from our network, we measure stylistic compatibility of furniture. We demonstrate our method with several 3D model style-compatibility results, and with an interactive system for modeling style-consistent scenes.en_US
dc.description.number7
dc.description.sectionheadersGeometry and Modeling
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume39
dc.identifier.doi10.1111/cgf.14126
dc.identifier.issn1467-8659
dc.identifier.pages57-68
dc.identifier.urihttps://doi.org/10.1111/cgf.14126
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14126
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.titleImage-Driven Furniture Style for Interactive 3D Scene Modelingen_US
Files
Collections