PDANet: Self-Supervised Monocular Depth Estimation Using Perceptual and Data Augmentation Consistency

In recent studies, self-supervised learning methods have been explored for monocular depth estimation. They minimize the reconstruction loss of images instead of depth information as a supervised signal. However, existing methods usually assume that the corresponding points in different views should...

Cijeli opis

Bibliografski detalji

Glavni autori:	Huachen Gao, Xiaoyu Liu, Meixia Qu, Shijie Huang
Format:	Artigo
Jezik:	Inglês
Izdano:	MDPI AG 2021-06-01
Serija:	Applied Sciences
Teme:	self-supervised depth estimation low texture perceptual consistency data augmentation
Online pristup:	https://www.mdpi.com/2076-3417/11/12/5383
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!