Deep Parametric Shape Predictions Using Distance Fields
Name
1904.08921.pdf
Description
Submitted version
Size
8.07 MB
Format
Adobe PDF
Checksum (MD5)
8345472276eaca20443b94f5c174e9f5
Author(s)
Smirnov, Dmitriy
Fisher, Matthew
Kim, Vladimir G
Zhang, Richard
Solomon, Justin
Date Issued
March 2020
Journal
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Smirnov, Dmitriy, Fisher, Matthew, Kim, Vladimir G, Zhang, Richard and Solomon, Justin. 2020. "Deep Parametric Shape Predictions Using Distance Fields." Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.
Version
Original manuscript
Abstract
© 2020 IEEE. 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.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/CVPR42600.2020.00064
