Conclusion and future development
- Sofia Imperatore
- © 2026 Author(s) |
- CC BY 4.0
- DOI: 10.36253/979-12-215-1002-7.10
This chapter concludes the thesis by summarizing the core contents and contributions and providing possible future research directions. Specifically, it reviews the integration of Computer Aided Geometric Design (CAGD) with Deep Learning (DL) to develop robust adaptive fitting schemes using THB-splines. The conclusion highlights the main thesis contributions, such as enhanced fitting via iteratively reweighted least squares and quasi-interpolation, data-driven parameterization through (graph) convolutional neural networks, and the design and development of the "moving parameterization" paradigm within adaptive (THB-)spline schemes. Finally, it outlines critical future research directions: employing DL for automatic boundary detection, developing quasi-conformal parameterizations to minimize geometric distortion, and extending the proposed methodologies to multi-patch frameworks for industrial CAD design.
- Keywords:
- Geometric Deep Learning,
- Computer Aided Geometric Design,
- boudary detection,
- multi-patch fitting,
- quasi-conformal parameterization,
Technical University of Eindhoven, Netherlands - ORCID: 0009-0003-9116-9978
Chapter Information
Chapter Title
Conclusion and future development
Authors
Sofia Imperatore
Language
English
DOI
10.36253/979-12-215-1002-7.10
Peer Reviewed
Publication Year
2026
Copyright Information
© 2026 Author(s)
Content License
Metadata License
Bibliographic Information
Book Title
Adaptive spline approximation: data-driven parameterization and CAD model (re-)construction
Authors
Sofia Imperatore
Peer Reviewed
Number of Pages
196
Publication Year
2026
Copyright Information
© 2026 Author(s)
Content License
Metadata License
Publisher Name
Firenze University Press
DOI
10.36253/979-12-215-1002-7
ISBN Print
979-12-215-1001-0
eISBN (pdf)
979-12-215-1002-7
eISBN (xml)
979-12-215-1003-4
Series Title
Premio Tesi di Dottorato Città di Firenze
Series ISSN
3103-3881
Series E-ISSN
3103-3989