TP-GAN: Simple Adversarial Network With Additional Player for Dense Depth Image Estimation

We present a simple yet robust monocular depth estimation technique by synthesizing a depth map image from a single RGB input image using the advantage of generative adversarial networks (GAN). We employ an additional sub-model termed refiner to extract local depth features, then combine it with the...

Full description

Bibliographic Details
Main Authors:	Hendra, A. (Author), Kanazawa, Y. (Author)
Format:	Article
Language:	English
Published:	Institute of Electrical and Electronics Engineers Inc. 2023
Subjects:	conditional GAN Conditional generative adversarial network Convolutional neural network Depth estimation Depth Estimation Generative adversarial network generative adversarial network (GAN) Generative adversarial networks Generator Image enhancement Image reconstruction Images reconstruction Job analysis Network architecture Neural networks Performance single image Single images Task analysis third player GAN Third player generative adversarial network
Online Access:	View Fulltext in Publisher View in Scopus

Internet

View Fulltext in Publisher
View in Scopus

TP-GAN: Simple Adversarial Network With Additional Player for Dense Depth Image Estimation

Internet

Similar Items