University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Stereo reconstruction using top-down cues

Hadfield, SJ, Lebeda, K and Bowden, R (2016) Stereo reconstruction using top-down cues Computer Vision and Image Understanding.

[img] Text
paper.pdf - Accepted version Manuscript
Restricted to Repository staff only
Available under License : See the attached licence file.

Download (17MB)
Text (licence)
Available under License : See the attached licence file.

Download (33kB) | Preview


We present a framework which allows standard stereo reconstruction to be unified with a wide range of classic top-down cues from urban scene understanding. The resulting algorithm is analogous to the human visual system where conflicting interpretations of the scene due to ambiguous data can be resolved based on a higher level understanding of urban environments. The cues which are reformulated within the framework include: recognising common arrangements of surface normals and semantic edges (e.g. concave, convex and occlusion boundaries), recognising connected or coplanar structures such as walls, and recognising collinear edges (which are common on repetitive structures such as windows). Recognition of these common configurations has only recently become feasible, thanks to the emergence of large-scale reconstruction datasets. To demonstrate the importance and generality of scene understanding during stereo-reconstruction, the proposed approach is integrated with 3 different state-of-the-art techniques for bottom-up stereo reconstruction. The use of high-level cues is shown to improve performance by up to 15 % on the Middlebury 2014 and KITTI datasets. We further evaluate the technique using the recently proposed HCI stereo metrics, finding significant improvements in the quality of depth discontinuities, planar surfaces and thin structures.

Item Type: Article
Subjects : Electronic Engineering
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering > Centre for Vision Speech and Signal Processing
Authors :
Date : 2016
Copyright Disclaimer : © 2016. This manuscript version is made available under the CC-BY-NC-ND 4.0 license
Uncontrolled Keywords : Stereo reconstruction, Scene understanding, biologically inspired, high level cues, bottom up, top down
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 03 Aug 2016 09:44
Last Modified : 03 Aug 2016 09:44

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800