Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation
Refereed conference paper presented and published in conference proceedings

摘要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 effective- ness of the proposed approach and establish new state of the art results on publicly available datasets.
著者Dan Xu, Elisa Ricci, Wanli Ouyang, Xiaogang Wang, Nicu Sebe
會議名稱2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
會議地點Honolulu, Hawaii
會議論文集題名Proceedings: 30th IEEE Conference on Computer Vision and Pattern Recognition CVPR 2017
頁次161 - 169

上次更新時間 2018-04-05 於 15:11