MSDC-Net: Multi-Scale Dense and Contextual Networks for Automated Disparity Map for Stereo Matching

04/25/2019
by   Zhibo Rao, et al.
0

Disparity prediction from stereo images is essential to computer vision applications including autonomous driving, 3D model reconstruction, and object detection. To predict accurate disparity map, we propose a novel deep learning architecture for detectingthe disparity map from a rectified pair of stereo images, called MSDC-Net. Our MSDC-Net contains two modules: multi-scale fusion 2D convolution and multi-scale residual 3D convolution modules. The multi-scale fusion 2D convolution module exploits the potential multi-scale features, which extracts and fuses the different scale features by Dense-Net. The multi-scale residual 3D convolution module learns the different scale geometry context from the cost volume which aggregated by the multi-scale fusion 2D convolution module. Experimental results on Scene Flow and KITTI datasets demonstrate that our MSDC-Net significantly outperforms other approaches in the non-occluded region.

READ FULL TEXT

page 3

page 4

page 5

research
04/25/2019

Multi-scale Cross-form Pyramid Network for Stereo Matching

Stereo matching plays an indispensable part in autonomous driving, robot...
research
06/23/2020

MSMD-Net: Deep Stereo Matching with Multi-scale and Multi-dimension Cost Volume

Deep end-to-end learning based stereo matching methods have achieved gre...
research
11/16/2016

On the Exploration of Convolutional Fusion Networks for Visual Recognition

Despite recent advances in multi-scale deep representations, their limit...
research
03/18/2018

Sdf-GAN: Semi-supervised Depth Fusion with Multi-scale Adversarial Networks

Fusing disparity maps from different algorithms to exploit their complem...
research
08/21/2021

L3C-Stereo: Lossless Compression for Stereo Images

A large number of autonomous driving tasks need high-definition stereo i...
research
03/05/2021

ES-Net: An Efficient Stereo Matching Network

Dense stereo matching with deep neural networks is of great interest to ...
research
03/24/2020

FADNet: A Fast and Accurate Network for Disparity Estimation

Deep neural networks (DNNs) have achieved great success in the area of c...

Please sign up or login with your details

Forgot password? Click here to reset