Title | ||
---|---|---|
Multi-scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation |
Abstract | ||
---|---|---|
This paper addresses the problem of depth estimation from a single still image. Inspired by recent works on multi-scale convolutional neural networks (CNN), we propose a deep model which fuses complementary information derived from multiple CNN side outputs. Different from previous methods, the integration is obtained by means of continuous Conditional Random Fields (CRFs). In particular, we propose two different variations, one based on a cascade of multiple CRFs, the other on a unified graphical model. By designing a novel CNN implementation of mean-field updates for continuous CRFs, we show that both proposed models can be regarded as sequential deep networks and that training can be performed end-to-end. Through extensive experimental evaluation we demonstrate the effectiveness of the proposed approach and establish new state of the art results on publicly available datasets. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/CVPR.2017.25 | 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
Keywords | DocType | Volume |
multiscale continuous CRFs,sequential deep networks,monocular depth estimation,single still image,multiscale convolutional neural networks,multiple CNN,multiple CRFs,unified graphical model,mean-field updates,continuous conditional random fields | Conference | abs/1704.02157 |
Issue | ISSN | ISBN |
1 | 1063-6919 | 978-1-5386-0458-8 |
Citations | PageRank | References |
58 | 1.31 | 31 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dan Xu | 1 | 342 | 16.39 |
Elisa Ricci 0002 | 2 | 1393 | 73.75 |
Wanli Ouyang | 3 | 2371 | 105.17 |
Xiaogang Wang | 4 | 9647 | 386.70 |
Nicu Sebe | 5 | 7013 | 403.03 |