Paper published in a book (Scientific congresses, symposiums and conference proceedings)
SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapes
CHERENKOVA, Kseniya; DUPONT, Elona Marcelle Eugénie; KACEM, Anis et al.
2023In Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
Peer reviewed
 

Files


Full Text
SepicNet_Sharp_Edges_Recovery_by_Parametric_Infere.pdf
Author preprint (6.57 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
3-d scans; 3-D shape; 3D models; 3d-modeling; 3D-scanners; 3D-scanning; End to end; Parametric inference; Parametrizations; Sharp edges; Computer Vision and Pattern Recognition; Electrical and Electronic Engineering
Abstract :
[en] 3D scanning as a technique to digitize objects in reality and create their 3D models, is used in many fields and areas. Though the quality of 3D scans depends on the technical characteristics of the 3D scanner, the common drawback is the smoothing of fine details, or the edges of an object. We introduce SepicNet, a novel deep network for the detection and parametrization of sharp edges in 3D shapes as primitive curves. To make the network end-to-end trainable, we formulate the curve fitting in a differentiable manner. We develop an adaptive point cloud sampling technique that captures the sharp features better than uniform sampling. The experiments were conducted on a newly introduced large-scale dataset of 50k 3D scans, where the sharp edge annotations were extracted from their parametric CAD models, and demonstrate significant improvement over state-of-the-art methods.
Disciplines :
Computer science
Author, co-author :
CHERENKOVA, Kseniya ;  University of Luxembourg ; Artec 3D
DUPONT, Elona Marcelle Eugénie ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
KACEM, Anis  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
Arzhannikov, Ilya;  Artec 3D
Gusev, Gleb;  Artec 3D
AOUADA, Djamila  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > CVI2
External co-authors :
yes
Language :
English
Title :
SepicNet: Sharp Edges Recovery by Parametric Inference of Curves in 3D Shapes
Publication date :
22 June 2023
Event name :
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Event place :
Vancouver, Can
Event date :
18-06-2023 => 22-06-2023
Main work title :
Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023
Publisher :
IEEE Computer Society
ISBN/EAN :
9798350302493
Peer reviewed :
Peer reviewed
Funding text :
The present project is supported by the National Research Fund, Luxembourg under the BRIDGES2021/IS/16849599/FREE-3D and IF/17052459/CASCADES projects, and by Artec 3D.
Available on ORBilu :
since 21 March 2024

Statistics


Number of views
86 (2 by Unilu)
Number of downloads
75 (0 by Unilu)

Scopus citations®
 
14
Scopus citations®
without self-citations
10
OpenAlex citations
 
8

Bibliography


Similar publications



Contact ORBilu