A unified and efficient semi-supervised learning framework for stereo matching

Open Webpage

Fudong Xu, Lin Wang, Huibin Li

Published: 01 Jan 2024, Last Modified: 14 Nov 2024Pattern Recognit. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•We propose the first semi-supervised stereo matching framework.•We integrate entropy minimization and consistent regularization for unlabeled data.•We achieve 1st on KITTI 2012 benchmark and 4th on KITTI 2015 benchmark.