ESTIMASI KEDALAMAN CITRA TUNGGAL LUAR RUANGAN MENGGUNAKAN JARINGAN GENERATIF

Andi Hendra, Yuri Yudhaswana Joefrie

Abstract

We propose a simple but robust monocular depth estimation using the advantage of the generative adversarial network (GAN) by synthesizing an image of the depth map from a single RGB input image. Unlike the regular scheme of GAN, we employ a conditional generative adversarial neural network (cGAN) to guide the generator to map the input image to the respective depth representation, which complements the GAN. Through extensive experiment validation, we confirmed the performance of our strategy on the KITTI outdoor data. We observed that our proposed method is shown to compare fairly over several previous single image depth estimation techniques and show a significant improvement of accuracy in depth estimation.

Keywords

Image depth estimation; Generative Adversarial networks; Deep learning; Conditional GAN;

Full Text:

PDF

References

D. Eigen, C. Puhrsch, and R. Fergus, “Depth map prediction from a single

image using a multi-scale deep network,” Proc. of the 27th Int. Conf. on

Neural Inf. Process. Syst., vol.2, pp.2366–2374, 2014.

A. Hendra and Y. Kanazawa, “Smaller Residual Network for Single Image

Depth Estimation,” IEICE Trans. Inf. and Syst., vol. E104-D, no.11, pp.1991–

, November 2021

I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S.

Ozair, and Y. Bengio, “Generative Adversarial Nets,” Advances in Neural

Information Processing Systems, vol.27, 2014.

P. Isola, J.y. Zhu, T. Zhou, and A.A. Efros, “Image-to-Image Translation with

Condiitonal Adversarial Networks,” IEEE Conference on Computer Vision

and Pattern Recognition (CVPR), pp.5967–5976, 2017.

D.h.Kwak and S.h.Lee,“A Novel Method for Estimating Monocular Depth

Using Cycle GAN and Segmentation,” Sensors, vol.20, no.9, 2020.

F. Liu, C. Shen, and G. Lin, “Deep convolutional neural fields for depth

estimation from a single image,” Proc. IEEE on CVPR, pp.5162–5170, June

Laina, C. Rupprecht, V. Belagiannis, F. Tombari, and N. Navab, “Deeper

depth prediction with fully convolutional residual networks,” Proc. of Int.

Conf. on 3D Vision, pp.239–248, October 2016.

B. G. J. Godard Clement, Aodha Oishin Mac, “Unsupervised monocular

depth estimation with left-right consistency,” Proc. IEEE on CVPR, pp.6602–

, July 2017.

D.S. Tan, C. Y. Yao, C. Ruiz, Jr., and H. Kai-Lung, “Single-Image Depth

Inference Using Generative Adversarial Networks,” Sensors, vol.19, no.7,

A.C. Kumar, S.M. Bhandarkar, and M. Prasad, “Monocular Depth Prediction

using Generative Adversarial Networks,” IEEE/CVF Conference on

Computer Vision and Pattern Recognition Workshops (CVPRW), pp.413–

, 2018.

M. Mirza and S. Osindero, “Conditional Generative Adversarial Nets,” ArXiv,

A. Geiger, P. Lenz, C. Stiller, and R. Urtasun, “Vision meets robotics: The

KITTI dataset,” International Journal of Robotics Research (IJRR), vol.32,

no.11, 2013.

A. Saxena, M. Sun, and A.Y. Ng, “Make3D: Learning 3D scene structure

from a single still image,” IEEE Trans. Pattern Anal. Mach. Intell., vol.31,

no.5, pp.824–840, May 2009.

Y. Kutznietzov, J. Stuchler, and B. Leibe, “Semi-supervised deep learning

for monocular depth map prediction,” In CVPR, 2017.

Refbacks

  • There are currently no refbacks.