Abstract | ||
---|---|---|
Cuboid detection is an essential step for understanding 3D structure of scenes. As most of indoor scene cuboids are actually objects, we propose in this paper an object-based approach to detect 3D cuboids in indoor RGB-D images. The proposed approach is learning-free and can handle general object classes rather than a limited pre-defined category set. In our approach, we first apply an extended version of the CPMC framework to generate a set of segment hypotheses, and fit a set of cuboid candidates. Given the candidate set, we select several cuboids that can provide plausible interpretations of the images by solving a Maximum Weighted Clique (MWC) problem. With this formulation, a set of ranked mid-level representations of the input image is obtained, and are further re-ranked by Maximal Marginal Relevance (MMR) measure to improve their diversity. Experimental results on NYU-V2 dataset shows that our method significantly outperforms the state-of-the-art, and shows impressive results. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/ICME.2015.7177405 | 2015 IEEE International Conference on Multimedia and Expo (ICME) |
Keywords | Field | DocType |
Cuboid detection,scene understanding,depth image,maximum weighted clique | Computer vision,Clique,Ranking,Pattern recognition,Computer science,Image segmentation,Artificial intelligence,Cuboid,RGB color model,Detector | Conference |
ISSN | Citations | PageRank |
1945-7871 | 0 | 0.34 |
References | Authors | |
14 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Han Zhang | 1 | 1 | 0.72 |
Xiaowu Chen | 2 | 605 | 45.05 |
Yu Zhang | 3 | 36 | 7.56 |
Jia Li | 4 | 524 | 42.09 |
qing li | 5 | 20 | 2.00 |
Xiaogang Wang | 6 | 9 | 1.13 |