3D car shape reconstruction from a contour sketch using GAN and lazy learning

Nozawa, N., Shum, H. P. H., Feng, Q., Ho, E. S. L. and Morishima, S. (2022) 3D car shape reconstruction from a contour sketch using GAN and lazy learning. Visual Computer, 38(4), pp. 1317-1330. (doi: 10.1007/s00371-020-02024-y)

[img] Text
276352.pdf - Published Version
Available under License Creative Commons Attribution.



3D car models are heavily used in computer games, visual effects, and even automotive designs. As a result, producing such models with minimal labour costs is increasingly more important. To tackle the challenge, we propose a novel system to reconstruct a 3D car using a single sketch image. The system learns from a synthetic database of 3D car models and their corresponding 2D contour sketches and segmentation masks, allowing effective training with minimal data collection cost. The core of the system is a machine learning pipeline that combines the use of a generative adversarial network (GAN) and lazy learning. GAN, being a deep learning method, is capable of modelling complicated data distributions, enabling the effective modelling of a large variety of cars. Its major weakness is that as a global method, modelling the fine details in the local region is challenging. Lazy learning works well to preserve local features by generating a local subspace with relevant data samples. We demonstrate that the combined use of GAN and lazy learning produces is able to produce high-quality results, in which different types of cars with complicated local features can be generated effectively with a single sketch. Our method outperforms existing ones using other machine learning structures such as the variational autoencoder.

Item Type:Articles
Glasgow Author(s) Enlighten ID:Ho, Dr Edmond S. L
Authors: Nozawa, N., Shum, H. P. H., Feng, Q., Ho, E. S. L., and Morishima, S.
College/School:College of Science and Engineering > School of Computing Science
Journal Name:Visual Computer
ISSN (Online):1432-2315
Published Online:16 April 2021
Copyright Holders:Copyright © 2021 The Authors
First Published:First published in Visual Computer 38(4): 1317-1330
Publisher Policy:Reproduced under a Creative Commons License

University Staff: Request a correction | Enlighten Editors: Update this record