Deep Parametric Shape Predictions using Distance Fields
This addresses the tedious manual process for artists and engineers in graphics and vision by automating parametric shape prediction, though it appears incremental as it builds on existing deep learning methods for geometric data.
The paper tackles the problem of generating parametric shapes from noisy or ambiguous geometric data, proposing a deep learning framework that uses distance fields to predict shape primitives, and demonstrates efficacy on 2D and 3D tasks like font vectorization and surface abstraction.
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.