ShadowGAN: Shadow synthesis for virtual objects with conditional adversarial networks

ShadowGAN: Shadow synthesis for virtual objects with conditional adversarial networks

Abstract We introduce ShadowGAN, a generative adversarial network (GAN) for synthesizing shadows for virtual objects inserted in images. Given a target image containing several existing objects with shadows, and an input source object with a specified insertion position, the network generates a real...

Full description

Bibliographic Details
Main Authors: Shuyang Zhang, Runze Liang, Miao Wang
Format: Article
Language:English
Published: SpringerOpen 2019-04-01
Series:Computational Visual Media
Subjects:
shadow synthesis
deep learning
generative adversarial networks
image synthesis
Online Access:http://link.springer.com/article/10.1007/s41095-019-0136-1

Internet

http://link.springer.com/article/10.1007/s41095-019-0136-1

Similar Items