DeepSpline: Data-Driven Reconstruction of Parametric Curves and Surfaces
This work addresses geometry reconstruction for computer-aided design and graphics, but it is incremental as it provides a complementary approach rather than a paradigm shift.
The paper tackled the problem of reconstructing parametric curves and surfaces from images or point clouds, which traditionally relies on local optimization methods requiring good initialization. They proposed a deep learning architecture for spline fitting, achieving complementary results to traditional methods.
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.