Find in Library

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.