3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics

被引:105
作者
Fu, Huan [1 ]
Cai, Bowen [1 ]
Gao, Lin [2 ]
Zhang, Ling-Xiao [2 ]
Wang, Jiaming [1 ]
Li, Cao [1 ]
Zeng, Qixun [1 ]
Sun, Chengyue [1 ]
Jia, Rongfei [1 ]
Zhao, Binqiang [1 ]
Zhang, Hao [3 ]
机构
[1] Alibaba Grp, Tao Technol Dept, Hangzhou, Zhejiang, Peoples R China
[2] Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China
[3] Simon Fraser Univ, GrUVi Graph U Vis, Burnaby, BC, Canada
来源
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) | 2021年
关键词
D O I
10.1109/ICCV48922.2021.01075
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We introduce 3D-FRONT (3D Furnished Rooms with layOuts and semaNTics), a new, large-scale, and comprehensive repository of synthetic indoor scenes highlighted by professionally designed layouts and a large number of rooms populated by high-quality textured 3D models with style compatibility. From layout semantics down to texture details of individual objects, our dataset is freely available to the academic community and beyond. Currently, 3D-FRONT contains 6,813 CAD houses, where 18,968 rooms diversely furnished by 3D objects, far surpassing all publicly available scene datasets. The 13,151 furniture objects all come with high-quality textures. While the floorplans and layout designs (i.e., furniture arrangements) are directly sourced from professional creations, the interior designs in terms of furniture styles, color, and textures have been carefully curated based on a recommender system we develop to attain consistent styles as expert designs. Furthermore, we release Trescope, a light-weight rendering tool, to support benchmark rendering of 2D images and annotations from 3D-FRONT. We demonstrate two applications, interior scene synthesis and texture synthesis, that are especially tailored to the strengths of our new dataset.
引用
收藏
页码:10913 / 10922
页数:10
相关论文
共 49 条
[1]  
Achlioptas P., 2018, INT C MACHINE LEARNI, P40
[2]  
[Anonymous], 2016, P IEEE INT C COMPUTE
[3]  
[Anonymous], 2005, P GRAPHICS INTERFACE
[4]   3D Scene Graph: A structure for unified semantics, 3D space, and camera [J].
Armeni, Iro ;
He, Zhi-Yang ;
Gwak, JunYoung ;
Zamir, Amir R. ;
Fischer, Martin ;
Malik, Jitendra ;
Savarese, Silvio .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :5663-5672
[5]  
Armeni Iro, 2017, arXiv preprint arXiv:1702.01105
[6]   Scan2CAD: Learning CAD Model Alignment in RGB-D Scans [J].
Avetisyan, Armen ;
Dahnert, Manuel ;
Dai, Angela ;
Savva, Manolis ;
Chang, Angel X. ;
Niessner, Matthias .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :2609-2618
[7]  
Chang AX., 2015, ShapeNet: an InformationRich 3D Model Repository, V1512, P03012
[8]   Hard Choices [J].
Chang, Ruth .
JOURNAL OF THE AMERICAN PHILOSOPHICAL ASSOCIATION, 2017, 3 (01) :1-21
[9]   Context-Aware Visual Compatibility Prediction [J].
Cucurull, Guillem ;
Taslakian, Perouz ;
Vazquez, David .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :12609-12618
[10]   ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes [J].
Dai, Angela ;
Chang, Angel X. ;
Savva, Manolis ;
Halber, Maciej ;
Funkhouser, Thomas ;
Niessner, Matthias .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :2432-2443