Line2depth: Indoor Depth Estimation from Line Drawings

Pavlov Sergey, Kanamori Yoshihiro, Endo Yuki

Abstract

Depth estimation from scenery line drawings has a number of applications, such as in painting software and 3D modeling. However, it has not received much attention because of the inherent ambiguity of line drawings. This paper proposes the first CNN-based method for estimating depth from single line drawings of indoor scenes. First, to combat the ambiguity of line drawings, we enrich the input line drawings by hallucinating colors, rough depth, and normal maps using a conditional GAN. Next, we obtain the final depth maps from the hallucinated data and input line drawings using a CNN for depth estimation. Our qualitative and quantitative evaluations demonstrate that our method works significantly better than conventional photo-aimed methods trained only with line drawings. Additionally, we confirmed that our results with hand-drawn indoor scenes are promising for use in practical applications.

Download


Paper Citation


in Harvard Style

Sergey P., Yoshihiro K. and Yuki E. (2021). Line2depth: Indoor Depth Estimation from Line Drawings.In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-488-6, pages 478-483. DOI: 10.5220/0010245104780483


in Bibtex Style

@conference{visapp21,
author={Pavlov Sergey and Kanamori Yoshihiro and Endo Yuki},
title={Line2depth: Indoor Depth Estimation from Line Drawings},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2021},
pages={478-483},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010245104780483},
isbn={978-989-758-488-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - Line2depth: Indoor Depth Estimation from Line Drawings
SN - 978-989-758-488-6
AU - Sergey P.
AU - Yoshihiro K.
AU - Yuki E.
PY - 2021
SP - 478
EP - 483
DO - 10.5220/0010245104780483