THB-Diff: a GPU-accelerated differentiable programming framework for THB-splines
Guardado en:
| Udgivet i: | Engineering with Computers vol. 40, no. 6 (Dec 2024), p. 3477 |
|---|---|
| Udgivet: |
Springer Nature B.V.
|
| Fag: | |
| Online adgang: | Citation/Abstract Full Text - PDF |
| Tags: |
Ingen Tags, Vær først til at tagge denne postø!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3139002977 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 0177-0667 | ||
| 022 | |a 1435-5663 | ||
| 024 | 7 | |a 10.1007/s00366-023-01929-1 |2 doi | |
| 035 | |a 3139002977 | ||
| 045 | 2 | |b d20241201 |b d20241231 | |
| 084 | |a 137654 |2 nlm | ||
| 245 | 1 | |a THB-Diff: a GPU-accelerated differentiable programming framework for THB-splines | |
| 260 | |b Springer Nature B.V. |c Dec 2024 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a We have developed a differentiable programming framework for truncated hierarchical B-splines (THB-splines), which can be used for several applications in geometry modeling, such as surface fitting and deformable image registration, and can be easily integrated with geometric deep learning frameworks. Differentiable programming is a novel paradigm that enables an algorithm to be differentiated via automatic differentiation, i.e., using automatic differentiation to compute the derivatives of its outputs with respect to its inputs or parameters. Differentiable programming has been used extensively in machine learning for obtaining gradients required in optimization algorithms such as stochastic gradient descent (SGD). While incorporating differentiable programming with traditional functions is straightforward, it is challenging when the functions are complex, such as splines. In this work, we extend the differentiable programming paradigm to THB-splines. THB-splines offer an efficient approach for complex surface fitting by utilizing a hierarchical tensor structure of B-splines, enabling local adaptive refinement. However, this approach brings challenges, such as a larger computational overhead and the non-trivial implementation of automatic differentiation and parallel evaluation algorithms. We use custom kernel functions for GPU acceleration in forward and backward evaluation that are necessary for differentiable programming of THB-splines. Our approach not only improves computational efficiency but also significantly enhances the speed of surface evaluation compared to previous methods. Our differentiable THB-splines framework facilitates faster and more accurate surface modeling with local refinement, with several applications in CAD and isogeometric analysis. | |
| 653 | |a Differentiation | ||
| 653 | |a Formability | ||
| 653 | |a Surface geometry | ||
| 653 | |a Graphics processing units | ||
| 653 | |a B spline functions | ||
| 653 | |a Image registration | ||
| 653 | |a Tensors | ||
| 653 | |a Programming | ||
| 653 | |a Algorithms | ||
| 653 | |a Acceleration | ||
| 653 | |a Deep learning | ||
| 653 | |a Machine learning | ||
| 653 | |a Kernel functions | ||
| 773 | 0 | |t Engineering with Computers |g vol. 40, no. 6 (Dec 2024), p. 3477 | |
| 786 | 0 | |d ProQuest |t Advanced Technologies & Aerospace Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3139002977/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3139002977/fulltextPDF/embedded/6A8EOT78XXH2IG52?source=fedsrch |