NURBS-Diff: A Differentiable Programming Module for NURBS
This addresses the challenge of using CAD-standard NURBS in deep learning for applications in engineering and design, though it appears incremental as it builds on existing differentiable programming concepts.
The authors tackled the problem of integrating NURBS representations from CAD with deep learning by proposing a differentiable NURBS module, which enables tasks like curve fitting and point cloud reconstruction with improved performance in certain frameworks.
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.