Depth estimation of a single RGB image with semi-supervised two-stage regression

Full resolution depth is required in many realworld engineering applications. However, exist depth sensorsonly offer sparse depth sample points with limited resolutionand noise, e.g., LiDARs. We here propose a deep learningbased full resolution depth recovery method from monocularimages and corresponding sparse depth measurements of targetenvironment. The novelty of our idea is that the structure similarinformation between the RGB image and depth image is used torefine the dense depth estimation result. This important similarstructure information can be found using a correlation layerin the regression neural network. We show that the proposedmethod can achieve higher estimation accuracy compared tothe state of the art methods. The experiments conducted on theNYU Depth V2 prove the novelty of our idea.<br>

Download Full-text

Depth estimation from a single RGB image using target foreground and background scene variations

Computers & Electrical Engineering ◽

10.1016/j.compeleceng.2021.107349 ◽

2021 ◽

Vol 94 ◽

pp. 107349

Author(s):

P.J.A. Alphonse ◽

K.V. Sriharsha

Keyword(s):

Depth Estimation ◽

Rgb Image

Download Full-text

A Two-Stage Correlation Method for Stereoscopic Depth Estimation

2010 International Conference on Digital Image Computing: Techniques and Applications ◽

10.1109/dicta.2010.49 ◽

2010 ◽

Cited By ~ 29

Author(s):

Nils Einecke ◽

Julian Eggert

Keyword(s):

Correlation Method ◽

Depth Estimation ◽

Stereoscopic Depth ◽

Two Stage

Download Full-text

GENERATING ARTIFICIAL NEAR INFRARED SPECTRAL BAND FROM RGB IMAGE USING CONDITIONAL GENERATIVE ADVERSARIAL NETWORK

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-v-3-2020-279-2020 ◽

2020 ◽

Vol V-3-2020 ◽

pp. 279-285

Author(s):

X. Yuan ◽

J. Tian ◽

P. Reinartz

Keyword(s):

Near Infrared ◽

Spectral Band ◽

Depth Estimation ◽

Absolute Error ◽

Physical Models ◽

Generative Adversarial Networks ◽

Surface Model ◽

Generative Adversarial Network ◽

Sensing Applications ◽

Rgb Image

Abstract. Near infrared bands (NIR) provide rich information for many remote sensing applications. In addition to deriving useful indices to delineate water and vegetation, near infrared channels could also be used to facilitate image pre-processing. However, synthesizing bands from RGB spectrum is not an easy task. The inter-correlations between bands are not clearly identified in physical models. Generative adversarial networks (GAN) have been used in many tasks such as generating photorealistic images, monocular depth estimation and Digital Surface Model (DSM) refinement etc. Conditional GAN is different in that it observes some data as a condition. In this paper, we explore a cGAN network structure to generate a NIR spectral band that is conditioned on the input RGB image. We test different discriminators and loss functions, and evaluate results using various metrics. The best simulated NIR channel has a mean absolute error of around 5 percent in Sentinel-2 dataset. In addition, the simulated NIR image can correctly distinguish between various classes of landcover.

Download Full-text

PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation

10.1109/3dv53792.2021.00074 ◽

2021 ◽

Author(s):

Yuyan Li ◽

Zhixin Yan ◽

Ye Duan ◽

Liu Ren

Keyword(s):

Depth Estimation ◽

Two Stage

Download Full-text

Efficient Multilevel Architecture for Depth Estimation from a Single Image

Electronic Imaging ◽

10.2352/issn.2470-1173.2020.14.coimg-377 ◽

2020 ◽

Vol 2020 (14) ◽

pp. 377-1-377-7

Author(s):

Bruno Artacho ◽

Nilesh Pandey ◽

Andreas Savakis

Keyword(s):

Deep Learning ◽

Autonomous Navigation ◽

Depth Estimation ◽

Local Information ◽

Single Image ◽

Learning Methods ◽

Computational Burden ◽

Multiple Levels ◽

Monocular Depth ◽

Rgb Image

Monocular depth estimation is an important task in scene understanding with applications to pose, segmentation and autonomous navigation. Deep Learning methods relying on multilevel features are currently used for extracting local information that is used to infer depth from a single RGB image. We present an efficient architecture that utilizes the features from multiple levels with fewer connections compared to previous networks. Our model achieves comparable scores for monocular depth estimation with better efficiency on the memory requirements and computational burden.

Download Full-text