arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.14547cs.LGcs.CV
收藏

NURBS的可微程序设计模块--DBS-Diff

NURBS-Diff: A Differentiable Programming Module for NURBS

Iowa State University(爱荷华州立大学);New York University(纽约大学)

Anjana Deva Prasad, Aditya Balu, Harshil Shah, Soumik Sarkar, Chinmay Hegde, Adarsh Krishnamurthy

摘要:

使用非均匀有理B样条(NURBS)的边界表示(B-reps)是CAD中使用的事实标准,但它们在基于深度学习的方法中的实用性尚未得到充分研究。我们提出了一个可微的NURBS模块来集成CAD模型的NURBS表示与深度学习方法。我们用数学方法定义NURBS曲线或曲面相对于输入参数(控制点、权重和节点向量)的导数。这些导数用于定义用于执行“向后”评估以训练深度学习模型的近似雅可比矩阵。我们使用GPU加速算法实现了NURBS模块,并将其与流行的深度学习框架PyTorch集成。我们证明了我们的NURBS模块在执行CAD操作,如曲线或曲面拟合和曲面偏移的功效。此外,我们展示了它在深度学习中用于无监督点云重建和强制分析约束的实用性。这些示例表明,我们的模块在某些深度学习框架中表现更好,并且可以直接与任何需要NURBS的深度学习框架集成。

英文摘要:

Boundary representations (B-reps) using Non-Uniform Rational B-splines (NURBS) are the de facto standard used in CAD, but their utility in deep learning-based approaches is not well researched. We propose a differentiable NURBS module to integrate NURBS representations of CAD models with deep learning methods. We mathematically define the derivatives of the NURBS curves or surfaces with respect to the input parameters (control points, weights, and the knot vector). These derivatives are used to define an approximate Jacobian used for performing the "backward" evaluation to train the deep learning models. We have implemented our NURBS module using GPU-accelerated algorithms and integrated it with PyTorch, a popular deep learning framework. We demonstrate the efficacy of our NURBS module in performing CAD operations such as curve or surface fitting and surface offsetting. Further, we show its utility in deep learning for unsupervised point cloud reconstruction and enforce analysis constraints. These examples show that our module performs better for certain deep learning frameworks and can be directly integrated with any deep-learning framework requiring NURBS.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑