Sketch2Tooncity: sketch-based city generation using neurosymbolic model

Junya Kanda; Yi He; Haoran Xie; Kazunori Miyata

doi:10.1117/12.3018858

2 May 2024 Sketch2Tooncity: sketch-based city generation using neurosymbolic model

Junya Kanda, Yi He, Haoran Xie, Kazunori Miyata

Proceedings Volume 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024; 1316424 (2024) https://doi.org/10.1117/12.3018858
Event: International Workshop on Advanced Imaging Technology (IWAIT) 2024, 2024, Langkawi, Malaysia

Abstract

In this study, we propose an efficient city-generation method based on user sketches. The proposed framework combines Conditional Generative Adversarial Networks(cGAN) and procedural modeling, which we call the Neurosymbolic Model. For cGAN training, the data set needs to consist of linked input and output pairs, so first the building of random height is generated using Perlin noise as the training data set. Then, the building contours are extracted by morphological transformation. For training, we use pairs of height maps created from the city data and sketches extracted by morphological transformation. Allowing users to generate diverse and satisfying cities from freehand sketches.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Junya Kanda, Yi He, Haoran Xie, and Kazunori Miyata "Sketch2Tooncity: sketch-based city generation using neurosymbolic model", Proc. SPIE 13164, International Workshop on Advanced Imaging Technology (IWAIT) 2024, 1316424 (2 May 2024); https://doi.org/10.1117/12.3018858

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available