arxivst stuff from arxiv that you should probably bookmark

Multi-Scale Continuous CRFs as Sequential Deep Networks for Monocular Depth Estimation

Abstract · Apr 7, 2017 09:39 ·

crf crfs depth cnn works depth rgb cascade pixel graphical cs-cv

Arxiv Abstract

  • Dan Xu
  • Elisa Ricci
  • Wanli Ouyang
  • Xiaogang Wang
  • Nicu Sebe

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.

Read the paper (pdf) »