eprintid: 1326253
rev_number: 40
eprint_status: archive
userid: 608
dir: disk0/01/32/62/53
datestamp: 2011-10-19 07:09:09
lastmod: 2021-11-15 01:55:14
status_changed: 2011-10-19 07:09:09
type: proceedings_section
metadata_visibility: show
item_issues_count: 0
creators_name: Campbell, NDF
creators_name: Vogiatzis, G
creators_name: Hernández, C
creators_name: Cipolla, R
title: Using multiple hypotheses to improve depth-maps for multi-view stereo
ispublished: pub
divisions: UCL
divisions: B04
divisions: C05
divisions: F48
note: D. Forsyth, P. Torr, and A. Zisserman (Eds.): ECCV 2008, Part I, LNCS 5302, pp. 766–779, 2008.  © Springer-Verlag Berlin Heidelberg 2008
abstract: We propose an algorithm to improve the quality of depth-maps used for Multi-View Stereo (MVS). Many existing MVS techniques make use of a two stage approach which estimates depth-maps from neighbouring images and then merges them to extract a final surface. Often the depth-maps used for the merging stage will contain outliers due to errors in the matching process. Traditional systems exploit redundancy in the image sequence (the surface is seen in many views), in order to make the final surface estimate robust to these outliers. In the case of sparse data sets there is often insufficient redundancy and thus performance degrades as the number of images decreases. In order to improve performance in these circumstances it is necessary to remove the outliers from the depth-maps. We identify the two main sources of outliers in a top performing algorithm: (1) spurious matches due to repeated texture and (2) matching failure due to occlusion, distortion and lack of texture. We propose two contributions to tackle these failure modes. Firstly, we store multiple depth hypotheses and use a spatial consistency constraint to extract the true depth. Secondly, we allow the algorithm to return an unknown state when the a true depth estimate cannot be found. By combining these in a discrete label MRF optimisation we are able to obtain high accuracy depth-maps with low numbers of outliers. We evaluate our algorithm in a multi-view stereo framework and find it to confer state-of-the-art performance with the leading techniques, in particular on the standard evaluation sparse data sets.
date: 2008
publisher: Springer-Verlag Berlin Heidelberg
official_url: http://dx.doi.org/10.1007/978-3-540-88682-2_58
vfaculties: VENG
oa_status: green
full_text_type: other
primo: open
primo_central: open_green
verified: verified_manual
elements_source: Manually entered
elements_id: 344414
doi: 10.1007/978-3-540-88682-2_58
isbn_13: 9783540886815
lyricists_name: Campbell, Neill
lyricists_id: NCAMP92
full_text_status: public
series: Lecture Notes in Computer Science
volume: 5302
place_of_pub: Germany
pagerange: 766-779
event_title: 10th European Conference on Computer Vision
book_title: Computer Vision – ECCV 2008
citation:        Campbell, NDF;    Vogiatzis, G;    Hernández, C;    Cipolla, R;      (2008)    Using multiple hypotheses to improve depth-maps for multi-view stereo.                     In:  Computer Vision – ECCV 2008.  (pp. pp. 766-779).  Springer-Verlag Berlin Heidelberg: Germany.       Green open access   
 
document_url: https://discovery.ucl.ac.uk/id/eprint/1326253/1/campbell_eccv08_multi_hypo_dm.pdf