EBStereo: edge-based loss function for real-time stereo matching

Deep learning-based stereo matching has made significant progress, but it still faces challenges: The disparity prediction error maps of current models show that errors are concentrated primarily on object boundaries. We find that executing the smooth L1 loss function on the entire region during ste...

Full description

Saved in:

Bibliographic Details
Published in:	The Visual computer Vol. 40; no. 4; pp. 2975 - 2986
Main Authors:	Bi, Weijie, Chen, Ming, Wu, Dongliu, Lu, Shenglian
Format:	Journal Article
Language:	English
Published:	Berlin/Heidelberg Springer Berlin Heidelberg 01.04.2024 Springer Nature B.V
Subjects:	Accuracy Algorithms Artificial Intelligence Computer Graphics Computer Science Deep learning Design Embedding Frames per second Image Processing and Computer Vision Matching Neural networks Original Article Real time Deep learning Loss function Feature fusion Stereo matching Bilateral grid learning
ISSN:	0178-2789, 1432-2315
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!