DeepSpline: Data-Driven Reconstruction of Parametric Curves and Surfaces

TL;DR

DeepSpline introduces a deep learning approach for reconstructing spline curves and surfaces from images or point clouds, offering an alternative to traditional optimization methods that require close initializations.

Contribution

It presents a novel neural network architecture that adapts to spline fitting tasks, enhancing reconstruction quality and robustness compared to classical optimization-based methods.

Findings

Effective reconstruction of spline curves and surfaces from various inputs

Improved robustness over traditional optimization methods

Versatile application to images and point clouds

Abstract

Reconstruction of geometry based on different input modes, such as images or point clouds, has been instrumental in the development of computer aided design and computer graphics. Optimal implementations of these applications have traditionally involved the use of spline-based representations at their core. Most such methods attempt to solve optimization problems that minimize an output-target mismatch. However, these optimization techniques require an initialization that is close enough, as they are local methods by nature. We propose a deep learning architecture that adapts to perform spline fitting tasks accordingly, providing complementary results to the aforementioned traditional methods. We showcase the performance of our approach, by reconstructing spline curves and surfaces based on input images or point clouds.