Efficient Multi-Scale Stereo-Matching Network Using Adaptive Cost Volume Filtering

While recent deep learning-based stereo-matching networks have shown outstanding advances, there are still some unsolved challenges. First, most state-of-the-art stereo models employ 3D convolutions for 4D cost volume aggregation, which limit the deployment of networks for resource-limited mobile en...

Full description

Bibliographic Details

Published in:	Sensors
Main Authors:	Suyeon Jeon, Yong Seok Heo
Format:	Article
Language:	English
Published:	MDPI AG 2022-07-01
Subjects:	deep learning stereo matching knowledge distillation cost volume filtering lightweight network
Online Access:	https://www.mdpi.com/1424-8220/22/15/5500