UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

DepthCut: Improved Depth Edge Estimation Using Multiple Unreliable Channels

Guerrero, P; Winnemöller, H; Li, W; Mitra, NJ; (2017) DepthCut: Improved Depth Edge Estimation Using Multiple Unreliable Channels. In: Bærentzen, J.A. and Hildebrandt, K, (eds.) Proceedings of the Symposium on Geometry Processing 2017. The Eurographics Association: London, UK. Green open access

[img]
Preview
Text
Guerrero 2018_Article_DepthCutImprovedDepthEdgeEstim.pdf - ["content_typename_Published version" not defined]

Download (9MB) | Preview

Abstract

In the context of scene understanding, a variety of methods exists to estimate different information channels from mono or stereo images, including disparity, depth, and normals. Although several advances have been reported in the recent years for these tasks, the estimated information is often imprecise particularly near depth discontinuities or creases. Studies have however shown that precisely such depth edges carry critical cues for the perception of shape, and play important roles in tasks like depth-based segmentation or foreground selection. Unfortunately, the currently extracted channels often carry conflicting signals, making it difficult for subsequent applications to effectively use them. In this paper, we focus on the problem of obtaining high-precision depth edges (i.e., depth contours and creases) by jointly analyzing such unreliable information channels. We propose DepthCut, a data-driven fusion of the channels using a convolutional neural network trained on a large dataset with known depth. The resulting depth edges can be used for segmentation, decomposing a scene into depth layers with relatively flat depth, or improving the accuracy of the depth estimate near depth edges by constraining its gradients to agree with these edges. Quantitatively, we compare against 15 variants of baselines and demonstrate that our depth edges result in an improved segmentation performance and an improved depth estimate near depth edges compared to data-agnostic channel fusion. Qualitatively, we demonstrate that the depth edges result in superior segmentation and depth orderings.

Type: Proceedings paper
Title: DepthCut: Improved Depth Edge Estimation Using Multiple Unreliable Channels
Event: Symposium on Geometry Processing 2017
Open access status: An open access version is available from UCL Discovery
DOI: 10.2312/sgp.20171202
Publisher version: https://doi.org/10.2312/sgp.20171202
Language: English
Additional information: This work is licensed under a Creative Commons Attribution 4.0 International License. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in the credit line; if the material is not included under the Creative Commons license, users will need to obtain permission from the license holder to reproduce the material. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/
UCL classification: UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: http://discovery.ucl.ac.uk/id/eprint/1557768
Downloads since deposit
58Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item