Image-Driven Furniture Style for Interactive 3D Scene Modeling
Document Type
Article
Publication Date
10-1-2020
Abstract
Creating 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.
Identifier
85096418465 (Scopus)
Publication Title
Computer Graphics Forum
External Full Text Location
https://doi.org/10.1111/cgf.14126
e-ISSN
14678659
ISSN
01677055
First Page
57
Last Page
68
Issue
7
Volume
39
Recommended Citation
Weiss, Tomer; Yildiz, Ilkay; Agarwal, Nitin; Ataer-Cansizoglu, Esra; and Choi, Jae Woo, "Image-Driven Furniture Style for Interactive 3D Scene Modeling" (2020). Faculty Publications. 4974.
https://digitalcommons.njit.edu/fac_pubs/4974
