Deep Parametric Shape Predictions Using Distance Fields

Dmitriy Smirnov, Matthew Fisher, Vladimir G. Kim, Richard Zhang, Justin Solomon; The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 561-570

Abstract


Many tasks in graphics and vision demand machinery for converting shapes into consistent representations with sparse sets of parameters; these representations facilitate rendering, editing, and storage. When the source data is noisy or ambiguous, however, artists and engineers often manually construct such representations, a tedious and potentially time-consuming process. While advances in deep learning have been successfully applied to noisy geometric data, the task of generating parametric shapes has so far been difficult for these methods. Hence, we propose a new framework for predicting parametric shape primitives using deep learning. We use distance fields to transition between shape parameters like control points and input data on a pixel grid. We demonstrate efficacy on 2D and 3D tasks, including font vectorization and surface abstraction.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Smirnov_2020_CVPR,
author = {Smirnov, Dmitriy and Fisher, Matthew and Kim, Vladimir G. and Zhang, Richard and Solomon, Justin},
title = {Deep Parametric Shape Predictions Using Distance Fields},
booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}
}