Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Building Scene Models by Completing and Hallucinating Depth and Semantics
 
conference paper

Building Scene Models by Completing and Hallucinating Depth and Semantics

Liu, Miaomiao
•
He, Xuming
•
Salzmann, Mathieu
2016
Computer Vision - Eccv 2016, Pt Vi
European Conference on Computer Vision (ECCV)

Building 3D scene models has been a longstanding goal of computer vision. The great progress in depth sensors brings us one step closer to achieving this in a single shot. However, depth sensors still produce imperfect measurements that are sparse and contain holes. While depth completion aims at tackling this issue, it ignores the fact that some regions of the scene are occluded by the foreground objects. Building a scene model would therefore require to hallucinate the depth behind these objects. In contrast with existing methods that either rely on manual input, or focus on the indoor scenario, we introduce a fully-automatic method to jointly complete and hallucinate depth and semantics in challenging outdoor scenes. To this end, we develop a two-layer model representing both the visible information and the hidden one. At the heart of our approach lies a formulation based on the Mumford-Shah functional, for which we derive an effective optimization strategy. Our experiments evidence that our approach can accurately fill the large holes in the input depth maps, segment the different kinds of objects in the scene, and hallucinate the depth and semantics behind the foreground objects.

  • Files
  • Details
  • Metrics
Loading...
Thumbnail Image
Name

LiuHeSalzmannECCV16.pdf

Access type

openaccess

Size

3.92 MB

Format

Adobe PDF

Checksum (MD5)

2a7a67076fbcef71c237678eb2435ab4

Loading...
Thumbnail Image
Name

LiuHeSalzmannECCV16Supp.pdf

Access type

openaccess

Size

6.22 MB

Format

Adobe PDF

Checksum (MD5)

c076461076505057c119d0eb29451478

Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés