An Innovative Saliency Guided ROI Selection Model for Panoramic Images Compression

Saliency detection has been an increasingly important tool for ROI selection in image compression. Most previous works on saliency detection are dedicated to conventional images, however, with the rapid development of VR or AR technology, it is becoming more and more important to obtain visual attention for panoramic images. Meanwhile, panoramic images have more potential for improvement in compression performance compared with the conventional case. In this work, we propose an innovative saliency guided ROI selection model. Extensive evaluations show the proposed approach outperforms other methods in saliency accuracy especially for panoramic images. Meanwhile, we improve the compression quality of standard JPEG by using a higher bit rate to encode image regions flagged by our model and lower bit rate elsewhere in the image.