# Deep Parametric Shape Predictions using Distance Fields

## TL;DR

This paper introduces a deep learning framework that predicts parametric shape primitives from noisy data using distance fields, improving shape representation tasks like font vectorization and surface abstraction.

## Contribution

The novel approach leverages distance fields to connect shape parameters with input data, enabling effective 2D and 3D shape predictions from noisy inputs.

## Key findings

- Effective on font vectorization tasks
- Successful in 3D surface abstraction
- Handles noisy and ambiguous data well

## 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.