EdgeStereo: A Context Integrated Residual Pyramid Network for Stereo Matching

03/14/2018
by   Xiao Song, et al.
0

Recently convolutional neural network (CNN) promotes the development of stereo matching greatly. Especially those end-to-end stereo methods achieve best performance. However less attention is paid on encoding context information, simplifying two-stage disparity learning pipeline and improving details in disparity maps. Differently we focus on these problems. Firstly, we propose an one-stage context pyramid based residual pyramid network (CP-RPN) for disparity estimation, in which a context pyramid is embedded to encode multi-scale context clues explicitly. Next, we design a CNN based multi-task learning network called EdgeStereo to recover missing details in disparity maps, utilizing mid-level features from edge detection task. In EdgeStereo, CP-RPN is integrated with a proposed edge detector HED_β based on two-fold multi-task interactions. The end-to-end EdgeStereo outputs the edge map and disparity map directly from a stereo pair without any post-processing or regularization. We discover that edge detection task and stereo matching task can help each other in our EdgeStereo framework. Comprehensive experiments on stereo benchmarks such as Scene Flow and KITTI 2015 show that our method achieves state-of-the-art performance.

READ FULL TEXT

page 2

page 13

page 14

research
03/05/2019

EdgeStereo: An Effective Multi-Task Learning Network for Stereo Matching and Edge Detection

Recently, leveraging on the development of end-to-end convolutional neur...
research
06/25/2019

End-to-End Learning of Multi-scale Convolutional Neural Network for Stereo Matching

Deep neural networks have shown excellent performance in stereo matching...
research
12/31/2016

Improved Stereo Matching with Constant Highway Networks and Reflective Confidence Learning

We present an improved three-step pipeline for the stereo matching probl...
research
08/25/2019

Depth-AGMNet: an Atrous Granular Multiscale Stereo Network Based on Depth Edge Auxiliary Task

Recently, end-to-end convolutional neural networks have achieved remarka...
research
12/04/2017

Learning Deep Correspondence through Prior and Posterior Feature Constancy

Stereo matching algorithms usually consist of four steps, including matc...
research
06/22/2020

ResFPN: Residual Skip Connections in Multi-Resolution Feature Pyramid Networks for Accurate Dense Pixel Matching

Dense pixel matching is required for many computer vision algorithms suc...
research
04/03/2019

StereoDRNet: Dilated Residual Stereo Net

We propose a system that uses a convolution neural network (CNN) to esti...

Please sign up or login with your details

Forgot password? Click here to reset