Harald Steinlechner, Bernhard Rainer, Michael Schwärzler, Georg Haaser, Attila Szabo, Stefan Maierhofer, Michael WimmerORCID iD
Adaptive Point-cloud Segmentation for Assisted Interactions
In Proceedings of the 33rd Symposium on Interactive 3D Graphics and Games, pages 14:1-14:9. May 2019.
[draft]

Information

  • Publication Type: Conference Paper
  • Workgroup(s)/Project(s):
  • Date: May 2019
  • ISBN: 978-1-4503-6310-5
  • Series: I3D ’19
  • Publisher: ACM
  • Location: Montreal, Quebec, Canada
  • Lecturer: Harald Steinlechner
  • Event: 33rd Symposium on Interactive 3D Graphics and Games
  • Editor: Blenkhorn, Ari Rapkin
  • DOI: 10.1145/3306131.3317023
  • Call for Papers: Call for Paper
  • Booktitle: Proceedings of the 33rd Symposium on Interactive 3D Graphics and Games
  • Conference date: 21. May 2019 – 23. May 2019
  • Pages: 14:1 – 14:9
  • Keywords: Pointcloud Segmentation, Shape Detection, Interactive Editing

Abstract

In this work, we propose an interaction-driven approach streamlined to support and improve a wide range of real-time 2D interaction metaphors for arbitrarily large pointclouds based on detected primitive shapes. Rather than performing shape detection as a costly pre-processing step on the entire point cloud at once, a user-controlled interaction determines the region that is to be segmented next. By keeping the size of the region and the number of points small, the algorithm produces meaningful results and therefore feedback on the local geometry within a fraction of a second. We can apply these finding for improved picking and selection metaphors in large point clouds, and propose further novel shape-assisted interactions that utilize this local semantic information to improve the user’s workflow.

Additional Files and Images

Additional images and videos

teaser: Our novel interactive approach for shape detection in point clouds allows for sophisticated interactions, like shape-assisted lasso selection, shape-assisted volumetric brush, and shape-assisted local LoD increment. teaser: Our novel interactive approach for shape detection in point clouds allows for sophisticated interactions, like shape-assisted lasso selection, shape-assisted volumetric brush, and shape-assisted local LoD increment.

Additional files

Weblinks

BibTeX

@inproceedings{STEINLECHNER-2019-APS,
  title =      "Adaptive Point-cloud Segmentation for Assisted Interactions",
  author =     "Harald Steinlechner and Bernhard Rainer and Michael
               Schw\"{a}rzler and Georg Haaser and Attila Szabo and Stefan
               Maierhofer and Michael Wimmer",
  year =       "2019",
  abstract =   "In this work, we propose an interaction-driven approach
               streamlined to support and improve a wide range of real-time
               2D interaction metaphors for arbitrarily large pointclouds
               based on detected primitive shapes. Rather than performing
               shape detection as a costly pre-processing step on the
               entire point cloud at once, a user-controlled interaction
               determines the region that is to be segmented next. By
               keeping the size of the region and the number of points
               small, the algorithm produces meaningful results and
               therefore feedback on the local geometry within a fraction
               of a second. We can apply these finding for improved picking
               and selection metaphors in large point clouds, and propose
               further novel shape-assisted interactions that utilize this
               local semantic information to improve the user’s workflow.",
  month =      may,
  isbn =       "978-1-4503-6310-5",
  series =     "I3D ’19",
  publisher =  "ACM",
  location =   "Montreal, Quebec, Canada",
  event =      "33rd Symposium on Interactive 3D Graphics and Games",
  editor =     "Blenkhorn, Ari Rapkin",
  doi =        "10.1145/3306131.3317023",
  booktitle =  "Proceedings of the 33rd Symposium on Interactive 3D Graphics
               and Games",
  pages =      "14:1--14:9",
  keywords =   "Pointcloud Segmentation, Shape Detection, Interactive
               Editing",
  URL =        "https://www.cg.tuwien.ac.at/research/publications/2019/STEINLECHNER-2019-APS/",
}