Distortion-Adaptive Salient Object Detection in 360? Omnidirectional Images

Image-based salient object detection (SOD) has been extensively explored in the past decades. However, SOD on 360? omnidirectional images is less studied owing to the lack of datasets with pixel-level annotations. Toward this end, this paper proposes a 360? image-based SOD dataset that contains 500 highresolution equirectangular images. We collect the representative equirectangular images from five mainstream 360? video datasets and manually annotate all objects and regions over these images with precise masks with a free-viewpoint way. To the best of our knowledge, it is the first public available dataset for salient object detection on 360? scenes. By observing this dataset, we find that distortion from projection, large-scale complex scene and small salient objects are the most prominent characteristics. Inspired by the founding, this paper proposes a baseline model for SOD on equirectangular images. In the proposed approach, we construct a distortion-adaptive module to dealwith the distortion caused by the equirectangular projection. In addition, a multi-scale contextual integration block is introduced to perceive and distinguish the rich scenes and objects in omnidirectional scenes. The whole network is organized in a progressively manner with deep supervision. Experimental results show the proposed baseline approach outperforms the top-performanced state-of-the-artmethods on 360? SOD dataset. Moreover, benchmarking results of the proposed baseline approach and other methods on 360? SOD dataset show the proposed dataset is very challenging, which also validate the usefulness of the proposed dataset and approach to boost the development of SOD on 360? omnidirectional scenes.