We propose a method to change the shadows cast by vehicles based on unpaired data, which is used to solve the problem of insufficient datasets for target detection in autonomous driving scenarios. This method can increase the training samples of road vehicles in different time periods and reduce the time needed to make complex annotations of datasets. Direct use of generative adversarial networks with cycle-consistency constraints can achieve mapping transformation of unpaired domains, but it is difficult to completely learn the mapping between different shadow domains. To solve this problem, V-ShadowGAN is proposed. First, to train the model, we construct an unpaired dataset of vehicle shadows in different time periods. Second, the shadow mask extractor and the shadow mask discriminator are constructed to extract shadow masks and guide the generation of shadows in the network. Finally, the spatial attention mechanism is added to the generator, which improves the overall quality of the generated image by changing the channel weight of the network and deepening the network. Various experiments show that V-ShadowGAN can effectively change the vehicle shadow.
Recent research on image translation has great progress with the development of generative adversarial networks (GANs) techniques. Generating high-resolution images with unsupervised architecture is one of the most challenging tasks for image translation. To this end, we propose an enhanced super-resolution generative adversarial network for image translation. First, for unlabeled datasets, we employ reconstructed consistency loss and mutual dual GANs, which contains two generators:GA → B, GB → A and two discriminators: DB, DA to develop an unsupervised learning framework. As reconstructed consistency loss is added between generators of GA → B and GB → A, our designed overall architecture can learn mapping function of different domains even without unpaired samples. In addition, the generator network includes encoder network, decoder network, and residual network with skip connections to generate high-resolution images with realistic details. Meanwhile, a stable normalization is proposed to stabilize the training of our discriminator networks. Finally, experimental results are carried out on six different datasets, demonstrating that our algorithms outperform the state-of-the-art methods in terms of the image quality and image resolution.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.