DeepSpline: Data-Driven Reconstruction of Parametric Curves and Surfaces
arXiv:1901.03781
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.
References in corpus (5)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
- On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
- A Point Set Generation Network for 3D Object Reconstruction from a Single Image
Cited by in corpus (11)
- Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis
- Deep Vectorization of Technical Drawings
- Learning Deformable Tetrahedral Meshes for 3D Reconstruction
- Fast Interactive Object Annotation with Curve-GCN
- Fast spline detection in high density microscopy data
- Learning Occupancy Function from Point Clouds for Surface Reconstruction
- Learning Manifold Patch-Based Representations of Man-Made Shapes
- Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid
- ScribbleBox: Interactive Annotation Framework for Video Object Segmentation
- Interactive Annotation of 3D Object Geometry using 2D Scribbles
- Engineering Sketch Generation for Computer-Aided Design