Skip to main navigation Skip to search Skip to main content

Proxy clouds for RGB-D stream processing: An insight

  • Université Paris-Saclay

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Modern RGB-D sensors are widely used for indoor 3D capture, with applications ranging from modeling to robotics, through gaming. Nevertheless, their use is limited by their low resolution, with frames often corrupted with noise, missing data and temporal inconsistencies. In order to cope with all these issues, we present Proxy Clouds, a multiplanar superstructure for unified real-time processing of RGB-D data. By generating and updating through time a single set of rich statistics parameterized over planar proxies from raw RGB-D data, several processing primitives can be applied to improve the quality of the RGB-D stream on-the-fly or lighten further operations. We illustrate the use of Proxy Clouds on several applications, including noise and temporal flickering removal, hole filling, resampling, color processing and compression. We present experiments performed with our framework in indoor scenes of different natures captured with a consumer depth sensor.

Original languageEnglish
Title of host publicationACM SIGGRAPH 2017 Talks, SIGGRAPH 2017
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450350082
DOIs
Publication statusPublished - 30 Jul 2017
Externally publishedYes
EventACM SIGGRAPH 2017 Talks - International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2017 - Los Angeles, United States
Duration: 30 Jul 20173 Aug 2017

Publication series

NameACM SIGGRAPH 2017 Talks, SIGGRAPH 2017

Conference

ConferenceACM SIGGRAPH 2017 Talks - International Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 2017
Country/TerritoryUnited States
CityLos Angeles
Period30/07/173/08/17

Keywords

  • Depth improvement
  • Plane detection
  • RGB-D stream
  • Scene analysis

Fingerprint

Dive into the research topics of 'Proxy clouds for RGB-D stream processing: An insight'. Together they form a unique fingerprint.

Cite this