Share Email Print
cover

Proceedings Paper • new

Monocular image depth estimation using dilated convolution and spatial pyramid polling structure
Author(s): Yinzhang Ding; Lu Lin; Lianghao Wang; Ming Zhang; Dongxiao Li; Haojie Ma
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this work, we address the problem of depth estimation from a single image. This is a challenging task because a single still image on its own does not give much depth cue, while recent advances in CNNs have made learning and predicting depth from a single image possible. We propose a new residual convolutional neural network (CNN) with dilated convolution and spatial pyramid pooling (SPP) structure to model the ambiguous mapping from a monocular 2D image to its depth map. The advantages of our method come from the use of dilated convolution and multi spatial scale information. Compared with existing deep CNN based methods, our method achieves much better results in indoor and outdoor scenarios.

Paper Details

Date Published: 6 May 2019
PDF: 7 pages
Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 1106918 (6 May 2019); doi: 10.1117/12.2524357
Show Author Affiliations
Yinzhang Ding, Zhejiang Univ. (China)
Zhejiang Provincial Key Lab. of Information Processing (China)
Lu Lin, Zhejiang Univ. (China)
Zhejiang Provincial Key Lab. of Information Processing (China)
Lianghao Wang, Zhejiang Univ. (China)
Zhejiang Provincial Key Lab. of Information Processing (China)
Nanjing Univ. (China)
Ming Zhang, Zhejiang Univ. (China)
Zhejiang Provincial Key Lab. of Information Processing (China)
Dongxiao Li, Zhejiang Univ. (China)
Zhejiang Provincial Key Lab. of Information Processing (China)
Haojie Ma, Zhejiang Univ. (China)
Zhejiang Provincial Key Lab. of Information Processing (China)


Published in SPIE Proceedings Vol. 11069:
Tenth International Conference on Graphics and Image Processing (ICGIP 2018)
Chunming Li; Hui Yu; Zhigeng Pan; Yifei Pu, Editor(s)

© SPIE. Terms of Use
Back to Top