Dilated Convolutional Neural Networks For Panoramic Image Saliency Prediction

Saliency prediction is an important way to understand human’s behavior and has a wide range of applications. Although lots of algorithms have been designed to predict saliency for planar images, there are few works for 360º images. In this paper, we propose an encoder-decoder network for panoramic image saliency prediction. Dilated convolutional layers are deployed in the network, which can extract more representative features and improve the accuracy of saliency prediction. To deal with the image distortions in 360º images, our network takes cube map format as input and processes six faces of cube map simultaneously. Respecting the saliency distribution of ground truth, we also propose a new data augmentation method to train the network, which is validated to be helpful for performance improvement. Extensive experiments show that our method gives new state-of-the-art results on 360º image saliency prediction.