TY - JOUR
T1 - 360 Degree Panorama Synthesis from Sequential Views Based on Improved FC-Densenets
AU - Zhu, Dandan
AU - Zhou, Qiangqiang
AU - Han, Tian
AU - Chen, Yongqing
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2019
Y1 - 2019
N2 - Inspired by the effectiveness of deep learning model, many panorama saliency prediction models based on deep learning began to emerge and achieved significant performance improvement. However, this kind of model requires a large number of labeled ground-truth data, and the existing panorama datasets are small-scale and difficult to train the deep learning models. To address this problem, we propose a novel panorama generative model for synthesizing realistic and sharp-looking panorama. In particular, our proposed panorama generative model consists of two sub-networks of generator and discriminator. At first, in order to make the synthesized panorama more realistic, we employ the improved Fully-Convolutional Densely Connected Convolutional Networks (FC-DenseNets) as the generator network. Secondly, we design a new correlation layer in the discriminator network, which can calculate the similarity between the generated image and the ground-truth image, and achieve the pixel level accuracy. The experimental results show that our proposed method outperforms other baseline work and has superior generalization ability to synthesize real-world data.
AB - Inspired by the effectiveness of deep learning model, many panorama saliency prediction models based on deep learning began to emerge and achieved significant performance improvement. However, this kind of model requires a large number of labeled ground-truth data, and the existing panorama datasets are small-scale and difficult to train the deep learning models. To address this problem, we propose a novel panorama generative model for synthesizing realistic and sharp-looking panorama. In particular, our proposed panorama generative model consists of two sub-networks of generator and discriminator. At first, in order to make the synthesized panorama more realistic, we employ the improved Fully-Convolutional Densely Connected Convolutional Networks (FC-DenseNets) as the generator network. Secondly, we design a new correlation layer in the discriminator network, which can calculate the similarity between the generated image and the ground-truth image, and achieve the pixel level accuracy. The experimental results show that our proposed method outperforms other baseline work and has superior generalization ability to synthesize real-world data.
KW - Virtual reality
KW - correlation layer
KW - generative model
KW - panorama
KW - saliency prediction
UR - http://www.scopus.com/inward/record.url?scp=85077180697&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077180697&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2019.2958111
DO - 10.1109/ACCESS.2019.2958111
M3 - Article
AN - SCOPUS:85077180697
VL - 7
SP - 180503
EP - 180511
JO - IEEE Access
JF - IEEE Access
M1 - 8926406
ER -