Distortion-adaptive Salient Object Detection in 360$^\circ$ Omnidirectional Images

TL;DR

This paper introduces a new dataset and a baseline model for salient object detection in 360° omnidirectional images, addressing challenges posed by distortion and complex scenes, and demonstrating improved performance over existing methods.

Contribution

The paper provides the first public dataset for 360° SOD and proposes a distortion-adaptive model with multi-scale contextual integration for better detection.

Findings

The dataset contains 500 annotated high-resolution 360° images.

The proposed model outperforms state-of-the-art methods on the dataset.

The dataset and model are effective in handling distortion and complex scenes.

Abstract

Image-based salient object detection (SOD) has been extensively explored in the past decades. However, SOD on 360$^\circ$ omnidirectional images is less studied owing to the lack of datasets with pixel-level annotations. Toward this end, this paper proposes a 360$^\circ$ image-based SOD dataset that contains 500 high-resolution equirectangular images. We collect the representative equirectangular images from five mainstream 360$^\circ$ 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$^\circ$ 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 these foundings, this paper proposes a baseline model for SOD on equirectangular images. In the proposed approach, we construct a distortion-adaptive module to deal with 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-art methods on 360$^\circ$ SOD dataset. Moreover, benchmarking results of the proposed baseline approach and other methods on 360$^\circ$ 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$^\circ$ omnidirectional scenes.