Imperial College London
Portrait Picture

DrStamatiaGiannarou

Faculty of Medicine, Department of Surgery & Cancer

Senior Lecturer
 
 
 
//

Contact

 

+44 (0)20 7594 3492stamatia.giannarou Website

 
 
//

Location

 

413Bessemer BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Huang:2021:10.1007/978-3-030-87202-1_22,
author = {Huang, B and Zheng, J-Q and Nguyen, A and Tuch, D and Vyas, K and Giannarou, S and Elson, DS},
doi = {10.1007/978-3-030-87202-1_22},
pages = {227--237},
publisher = {Springer},
title = {Self-supervised generative adverrsarial network for depth estimation in laparoscopic images},
url = {http://dx.doi.org/10.1007/978-3-030-87202-1_22},
year = {2021}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - Dense depth estimation and 3D reconstruction of a surgical scene are crucial steps in computer assisted surgery. Recent work has shown that depth estimation from a stereo image pair could be solved with convolutional neural networks. However, most recent depth estimation models were trained on datasets with per-pixel ground truth. Such data is especially rare for laparoscopic imaging, making it hard to apply supervised depth estimation to real surgical applications. To overcome this limitation, we propose SADepth, a new self-supervised depth estimation method based on Generative Adversarial Networks. It consists of an encoder-decoder generator and a discriminator to incorporate geometry constraints during training. Multi-scale outputs from the generator help to solve the local minima caused by the photometric reprojection loss, while the adversarial learning improves the framework generation quality. Extensive experiments on two public datasets show that SADepth outperforms recent state-of-the-art unsupervised methods by a large margin, and reduces the gap between supervised and unsupervised depth estimation in laparoscopic images.
AU  - Huang,B
AU  - Zheng,J-Q
AU  - Nguyen,A
AU  - Tuch,D
AU  - Vyas,K
AU  - Giannarou,S
AU  - Elson,DS
DO  - 10.1007/978-3-030-87202-1_22
EP  - 237
PB  - Springer
PY  - 2021///
SP  - 227
TI  - Self-supervised generative adverrsarial network for depth estimation in laparoscopic images
UR  - http://dx.doi.org/10.1007/978-3-030-87202-1_22
UR  - http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000712021400022&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=1ba7043ffcc86c417c072aa74d649202
UR  - https://link.springer.com/chapter/10.1007%2F978-3-030-87202-1_22
UR  - http://hdl.handle.net/10044/1/94151
ER  -
Download