Edinburgh Research Explorer

UDFNet: Unsupervised Disparity Fusion with Adversarial Networks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Related Edinburgh Organisations

Open Access permissions

Open

Documents

https://ieeexplore.ieee.org/document/8803180
Original languageEnglish
Title of host publication2019 26th IEEE International Conference on Image Processing (ICIP)
PublisherIEEE
Pages1765-1769
Number of pages5
ISBN (Electronic)978-1-5386-6249-6
ISBN (Print)978-1-5386-6250-2
DOIs
Publication statusPublished - 26 Aug 2019
Event26th IEEE International Conference on Image Processing (ICIP) - Taipei, Taiwan, Province of China
Duration: 22 Sep 201925 Sep 2019
http://2019.ieeeicip.org/index.php

Publication series

Name
PublisherInstitute of Electrical and Electronics Engineers
ISSN (Print)1522-4880
ISSN (Electronic)2381-8549

Conference

Conference26th IEEE International Conference on Image Processing (ICIP)
Abbreviated titleICIP 2019
CountryTaiwan, Province of China
CityTaipei
Period22/09/1925/09/19
Internet address

Abstract

Fusing disparity maps from different methods is an useful technique to get a refined disparity map by leveraging the complimentary advantage. We present a model for disparity fusion that uses an adversarial network, which can be trained without using ground truth disparity data. We input two initial disparity maps (from the left view) along with auxiliary information (gradient, left & right intensity image) into the generator and train the generator to output a refined disparity map registered on the left view. The refined left disparity map and left intensity image are used to reconstruct a fake right intensity image. Finally, the fake and real right intensity images (from the right stereo vision camera) are fed into a discriminator. The trained network’s architecture is effective for the fusion task (90 fps on Kitti2015). The accuracy is on par or even better than the state-of-art supervised methods. A demo video is available https://youtu.be/XTHOF3kZGsU.

Event

26th IEEE International Conference on Image Processing (ICIP)

22/09/1925/09/19

Taipei, Taiwan, Province of China

Event: Conference

Download statistics

No data available

ID: 87381920