Adaptive pointcloud segmentation for assisted interactions

Harald Steinlechner; Bernhard Rainer; Michael Schwarzler; Georg Haaser; Attila Szabo; Stefan Maierhofer; Michael Wimmer

doi:10.1145/3306131.3317023

Adaptive pointcloud segmentation for assisted interactions

Harald Steinlechner^*, Bernhard Rainer, Michael Schwarzler, Georg Haaser, Attila Szabo, Stefan Maierhofer, Michael Wimmer

^*Corresponding author for this work

Computer Graphics and Visualisation

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

2 Citations (Scopus)

146 Downloads (Pure)

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.

Original language	English
Title of host publication	Proceedings - I3D 2019
Subtitle of host publication	ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games
Editors	Stephen N. Spencer
Publisher	Association for Computing Machinery (ACM)
Pages	1-9
Number of pages	9
ISBN (Electronic)	9781450363105
DOIs	https://doi.org/10.1145/3306131.3317023
Publication status	Published - 21 May 2019
Event	2019 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, I3D 2019 - Montreal, Canada Duration: 21 May 2019 → 23 May 2019

Conference

Conference	2019 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, I3D 2019
Country/Territory	Canada
City	Montreal
Period	21/05/19 → 23/05/19

Keywords

Interactive Editing
Pointcloud Segmentation
Shape Detection

Access to Document

10.1145/3306131.3317023

PB-VRVis-2019-005Accepted author manuscript, 19 MB

Cite this

Steinlechner, H., Rainer, B., Schwarzler, M., Haaser, G., Szabo, A., Maierhofer, S., & Wimmer, M. (2019). Adaptive pointcloud segmentation for assisted interactions. In S. N. Spencer (Ed.), Proceedings - I3D 2019: ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (pp. 1-9). Article 3317023 Association for Computing Machinery (ACM). https://doi.org/10.1145/3306131.3317023

@inproceedings{20eb874292d94a949cfa173f85438a7b,

title = "Adaptive pointcloud segmentation for assisted interactions",

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.",

keywords = "Interactive Editing, Pointcloud Segmentation, Shape Detection",

author = "Harald Steinlechner and Bernhard Rainer and Michael Schwarzler and Georg Haaser and Attila Szabo and Stefan Maierhofer and Michael Wimmer",

year = "2019",

month = may,

day = "21",

doi = "10.1145/3306131.3317023",

language = "English",

pages = "1--9",

editor = "Spencer, {Stephen N.}",

booktitle = "Proceedings - I3D 2019",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

note = "2019 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, I3D 2019 ; Conference date: 21-05-2019 Through 23-05-2019",

}

Steinlechner, H, Rainer, B, Schwarzler, M, Haaser, G, Szabo, A, Maierhofer, S & Wimmer, M 2019, Adaptive pointcloud segmentation for assisted interactions. in SN Spencer (ed.), Proceedings - I3D 2019: ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games., 3317023, Association for Computing Machinery (ACM), pp. 1-9, 2019 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, I3D 2019, Montreal, Canada, 21/05/19. https://doi.org/10.1145/3306131.3317023

Adaptive pointcloud segmentation for assisted interactions. / Steinlechner, Harald; Rainer, Bernhard; Schwarzler, Michael et al.
Proceedings - I3D 2019: ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games. ed. / Stephen N. Spencer. Association for Computing Machinery (ACM), 2019. p. 1-9 3317023.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Adaptive pointcloud segmentation for assisted interactions

AU - Steinlechner, Harald

AU - Rainer, Bernhard

AU - Schwarzler, Michael

AU - Haaser, Georg

AU - Szabo, Attila

AU - Maierhofer, Stefan

AU - Wimmer, Michael

PY - 2019/5/21

Y1 - 2019/5/21

N2 - 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.

AB - 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.

KW - Interactive Editing

KW - Pointcloud Segmentation

KW - Shape Detection

UR - http://www.scopus.com/inward/record.url?scp=85066797383&partnerID=8YFLogxK

U2 - 10.1145/3306131.3317023

DO - 10.1145/3306131.3317023

M3 - Conference contribution

AN - SCOPUS:85066797383

SP - 1

EP - 9

BT - Proceedings - I3D 2019

A2 - Spencer, Stephen N.

PB - Association for Computing Machinery (ACM)

T2 - 2019 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games, I3D 2019

Y2 - 21 May 2019 through 23 May 2019

ER -

Adaptive pointcloud segmentation for assisted interactions

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this