Abstract | ||
---|---|---|
In this paper we study the problem of monocular relative depth perception in the wild. We introduce a simple yet effective method to automatically generate dense relative depth annotations from web stereo images, and propose a new dataset that consists of diverse images as well as corresponding dense relative depth maps. Further, an improved ranking loss is introduced to deal with imbalanced ordinal relations, enforcing the network to focus on a set of hard pairs. Experimental results demonstrate that our proposed approach not only achieves state-of-the-art accuracy of relative depth perception in the wild, but also benefits other dense per-pixel prediction tasks, e.g., metric depth estimation and semantic segmentation. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/CVPR.2018.00040 | 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition |
Keywords | Field | DocType |
dense relative depth maps,dense per-pixel prediction tasks,web stereo images,dense relative depth annotations,web stereo data supervision,monocular relative depth perception,metric depth estimation,imbalanced ordinal relations | Computer vision,Pattern recognition,Ranking,Ordinal number,Segmentation,Computer science,Network architecture,Image segmentation,Artificial intelligence,Depth perception,Monocular,Semantics | Conference |
ISSN | ISBN | Citations |
1063-6919 | 978-1-5386-6421-6 | 9 |
PageRank | References | Authors |
0.48 | 13 | 7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ke Xian | 1 | 55 | 8.99 |
Chunhua Shen | 2 | 4817 | 234.19 |
Zhiguo Cao | 3 | 314 | 44.17 |
Hao Lu | 4 | 140 | 20.86 |
Yang Xiao | 5 | 237 | 26.58 |
Ruibo Li | 6 | 9 | 0.81 |
Zhenbo Luo | 7 | 80 | 5.10 |