3.8 Proceedings Paper

End-to-End Training of Hybrid CNN-CRF Models for Stereo

Publisher

IEEE
DOI: 10.1109/CVPR.2017.159

Keywords

-

Funding

  1. research initiative Intelligent Vision Austria
  2. AIT
  3. Austrian Federal Ministry of Science, Research and Economy HRSM programme (BGBl. II) [292/2012]
  4. ERC starting grant HOMOVIS [640156]
  5. European Research Council (ERC) [640156] Funding Source: European Research Council (ERC)

Ask authors/readers for more resources

We propose a novel and principled hybrid CNN+CRF model for stereo estimation. Our model allows to exploit the advantages of both, convolutional neural networks (CNNs) and conditional random fields (CRFs) in an unified approach. The CNNs compute expressive features for matching and distinctive color edges, which in turn are used to compute the unary and binary costs of the CRF. For inference, we apply a recently proposed highly parallel dual block descent algorithm which only needs a small fixed number of iterations to compute a high-quality approximate minimizer. As the main contribution of the paper, we propose a theoretically sound method based on the structured output support vector machine (SSVM) to train the hybrid CNN+CRF model on large-scale data end-to-end. Our trained models perform very well despite the fact that we are using shallow CNNs and do not apply any kind of post-processing to the final output of the CRF. We evaluate our combined models on challenging stereo benchmarks such as Middlebury 2014 and Kitti 2015 and also investigate the performance of each individual component.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

3.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available