# DeepSpline: Data-Driven Reconstruction of Parametric Curves and Surfaces

arXiv: https://arxiv.org/abs/1901.03781 · HTML: https://mlsanity.com/paper/1901.03781/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jan 2019.

## Built on by (most cited first, 9 of 9)

- [Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis](https://mlsanity.com/paper/2111.04276/) (2021)
- [GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images](https://mlsanity.com/paper/2209.11163/) (2022)
- [Im2Vec: Synthesizing Vector Graphics without Vector Supervision](https://mlsanity.com/paper/2102.02798/) (2021)
- [Engineering Sketch Generation for Computer-Aided Design](https://mlsanity.com/paper/2104.09621/) (2021)
- [Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds](https://mlsanity.com/paper/2312.04962/) (2023)
- [Graph-Guided Deformation for Point Cloud Completion](https://mlsanity.com/paper/2112.01840/) (2021)
- [Fast spline detection in high density microscopy data](https://mlsanity.com/paper/2301.04460/) (2023)
- [MARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learning](https://mlsanity.com/paper/2110.04830/) (2021)
- [Historical Astronomical Diagrams Decomposition in Geometric Primitives](https://mlsanity.com/paper/2403.08721/) (2024)

## Abstract (arXiv)

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.