Learning to Approximate Directional Fields Defined over 2D Planes

Maria Taktasheva*Albert Matveev*Alexey ArtemovEvgeny Burnaev

Skolkovo Institute of Science and Technology

Analysis of Images, Social networks and Texts 2019

Examples of rasterized vector primitives with accompanying discretized ground-truth 2-PolyVector field derived according to our scheme


Reconstruction of directional fields is a need in many geometry processing tasks, such as image tracing, extraction of 3D geometric features, and finding principal surface directions. A common approach to the construction of directional fields from data relies on complex optimization procedures, which are usually poorly formalizeable, require a considerable computational effort, and do not transfer across applications. In this work, we propose a deep learning-based approach and study the expressive power and generalization ability.



Copy bibtex


If you have any questions about this work, please contact us under adase-3ddl@skoltech.ru.