InceptCurves: curve reconstruction using an inception network
Curve reconstruction is a fundamental task in many visual computing applications. In this paper, a data-driven approach for curve reconstruction is proposed. We present an inception layered deep neural network structure, capable of learning simultaneously the number of control points and their posit...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/180103 |
| _version_ | 1826117753632718848 |
|---|---|
| author | Khalilsaraei, Saeedeh Barzegar Komar, Alexander Zheng, Jianmin Augsdörfer, Ursula |
| author2 | College of Computing and Data Science |
| author_facet | College of Computing and Data Science Khalilsaraei, Saeedeh Barzegar Komar, Alexander Zheng, Jianmin Augsdörfer, Ursula |
| author_sort | Khalilsaraei, Saeedeh Barzegar |
| collection | NTU |
| description | Curve reconstruction is a fundamental task in many visual computing applications. In this paper, a data-driven approach for curve reconstruction is proposed. We present an inception layered deep neural network structure, capable of learning simultaneously the number of control points and their positions in order to reconstruct the curve. To train the network, a large set of general synthetic data is generated. The reconstructed uniform B-spline closely approximates any arbitrary input curve, with or without intersections. Because the network predicts the number of control points required for the B-spline reconstruction, redundancy is reduced in the curve representation. We demonstrate our approach on various examples. |
| first_indexed | 2024-10-01T04:32:31Z |
| format | Journal Article |
| id | ntu-10356/180103 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:32:31Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1801032024-09-17T02:26:39Z InceptCurves: curve reconstruction using an inception network Khalilsaraei, Saeedeh Barzegar Komar, Alexander Zheng, Jianmin Augsdörfer, Ursula College of Computing and Data Science Computer and Information Science Machine learning Curve reconstruction Curve reconstruction is a fundamental task in many visual computing applications. In this paper, a data-driven approach for curve reconstruction is proposed. We present an inception layered deep neural network structure, capable of learning simultaneously the number of control points and their positions in order to reconstruct the curve. To train the network, a large set of general synthetic data is generated. The reconstructed uniform B-spline closely approximates any arbitrary input curve, with or without intersections. Because the network predicts the number of control points required for the B-spline reconstruction, redundancy is reduced in the curve representation. We demonstrate our approach on various examples. Published version Open access funding provided by Graz University of Technology. 2024-09-17T02:26:39Z 2024-09-17T02:26:39Z 2024 Journal Article Khalilsaraei, S. B., Komar, A., Zheng, J. & Augsdörfer, U. (2024). InceptCurves: curve reconstruction using an inception network. Visual Computer, 40(7), 4805-4815. https://dx.doi.org/10.1007/s00371-024-03477-1 0178-2789 https://hdl.handle.net/10356/180103 10.1007/s00371-024-03477-1 2-s2.0-85195681785 7 40 4805 4815 en Visual Computer © 2024 The Author(s). Open Access. This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecomm ons.org/licenses/by/4.0/. application/pdf |
| spellingShingle | Computer and Information Science Machine learning Curve reconstruction Khalilsaraei, Saeedeh Barzegar Komar, Alexander Zheng, Jianmin Augsdörfer, Ursula InceptCurves: curve reconstruction using an inception network |
| title | InceptCurves: curve reconstruction using an inception network |
| title_full | InceptCurves: curve reconstruction using an inception network |
| title_fullStr | InceptCurves: curve reconstruction using an inception network |
| title_full_unstemmed | InceptCurves: curve reconstruction using an inception network |
| title_short | InceptCurves: curve reconstruction using an inception network |
| title_sort | inceptcurves curve reconstruction using an inception network |
| topic | Computer and Information Science Machine learning Curve reconstruction |
| url | https://hdl.handle.net/10356/180103 |
| work_keys_str_mv | AT khalilsaraeisaeedehbarzegar inceptcurvescurvereconstructionusinganinceptionnetwork AT komaralexander inceptcurvescurvereconstructionusinganinceptionnetwork AT zhengjianmin inceptcurvescurvereconstructionusinganinceptionnetwork AT augsdorferursula inceptcurvescurvereconstructionusinganinceptionnetwork |