This paper introduces a method for learning to generate line drawings from 3D models. Our architecture incorporates a differentiable module operating on geometric features of the 3D model, and an image-based module operating on view-based shape representations. At test time, geometric and view-based reasoning are combined with the help of a neural module to create a line drawing. The model is trained on a large number of crowdsourced comparisons of line drawings. Experiments demonstrate that our method achieves significant improvements in line drawing over the state-of-the-art when evaluated on standard benchmarks, resulting in drawings that are comparable to those produced by experienced human artists.
@article{arxiv.2003.10333,
title = {Neural Contours: Learning to Draw Lines from 3D Shapes},
author = {Difan Liu and Mohamed Nabail and Aaron Hertzmann and Evangelos Kalogerakis},
journal= {arXiv preprint arXiv:2003.10333},
year = {2020}
}