Reusable Architecture Growth for Continual Stereo Matching

arXiv:2404.00360v1 Announce Type: new
Abstract: The remarkable performance of recent stereo depth estimation models benefits from the successful use of convolutional neural networks to regress dense disparity. Akin to most tasks, this needs gathering training data that covers a number of heterogeneous scenes at deployment time. However, training samples are typically acquired continuously in practical applications, making the capability to learn new scenes continually even more crucial. For this purpose, we propose to perform continual stereo matching where a model …

abstract acquired architecture arxiv benefits continual convolutional neural networks cs.cv data deployment growth however networks neural networks performance samples tasks training training data type