DeepAI
Log In Sign Up

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

11/30/2016
by   Patrick Knöbelreiter, et al.
0

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.

READ FULL TEXT

page 4

page 7

page 8

page 12

page 13

page 14

page 15

11/08/2018

An End-to-end Approach to Semantic Segmentation with 3D CNN and Posterior-CRF in Medical Images

Fully-connected Conditional Random Field (CRF) is often used as post-pro...
12/06/2016

Deep Stereo Matching with Dense CRF Priors

Stereo reconstruction from rectified images has recently been revisited ...
05/06/2019

Simulating CRF with CNN for CNN

Combining CNN with CRF for modeling dependencies between pixel labels is...
12/06/2019

End-to-end Training of CNN-CRF via Differentiable Dual-Decomposition

Modern computer vision (CV) is often based on convolutional neural netwo...
03/28/2015

CRF Learning with CNN Features for Image Segmentation

Conditional Random Rields (CRF) have been widely applied in image segmen...
07/20/2017

Scalable Full Flow with Learned Binary Descriptors

We propose a method for large displacement optical flow in which local m...
09/10/2019

Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection

Recent saliency models extensively explore to incorporate multi-scale co...