Omnidirectional Image Quality Assessment With Knowledge Distillation

Omnidirectional images can be viewed through various projection formats. Different projection formats could offer different views, which may capture complementary information to boost feature representation effect. However, previous omnidirectional image quality assessment (OIQA) methods mostly focus on single projection format, the relationship between different projection contents is rarely explored. In this letter, we propose a knowledge distillation based OIQA (KD-OIQA) framework that improves quality feature representation capability of student network under the guidance of the quality feature representation of teacher network through different projection formats. Specially, we firstly train a teacher network with viewport images. Then, we distill the knowledge from teacher network into student network trained on the equirectangular projection (ERP) images for boosting the feature representation of student network. Based on recent advance regarding knowledge distillation by applying masks, we also design a masked distillation module to screen out effective information from teacher's features to achieve more efficient knowledge distillation effect. Finally, the student network extracts more comprehensive features from ERP images for quality prediction. Extensive experiments conducted on three OIQA databases demonstrate the effectiveness of the proposed framework.