Shuffle in 3D: A Lightweight Architecture for Stereo Matching

The deep learning-based stereo matching approaches commonly construct 3D cost volume with a Siamese network, and the 3D encoder-decoder architectures regularize 3D cost volume to generate disparity as output. Yet, the 3D encoder-decoder architectures produce tremendous parameters that causing huge t...

Full description

Bibliographic Details

Published in:	2021 IEEE 10th Global Conference on Consumer Electronics (GCCE) pp. 675 - 677
Main Authors:	Xiao, Jianqiang, Yamane, Satoshi
Format:	Conference Proceeding
Language:	English
Published:	IEEE 12.10.2021
Subjects:	3D ShuffleNet Computational efficiency Computer architecture Conferences Consumer electronics Costs lightweight 3D encoder-decoder Stereo Matching Three-dimensional displays Training
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!