Visual Saliency Guided Foveated Video Compression

Video compression has become increasingly crucial as video resolution and bitrate have surged in recent years. However, most widely applied methods do not fully exploit the characteristics of Human Visual System (HVS) to reduce perceptual redundancy videos. In this paper, we propose a novel method that integrates visual saliency information with foveation redundancy. We present new approach subsample restore input image using data, which allocates more space for salient regions less non-salient ones. analyze entropy frames before after applying our algorithm demonstrate proposed reduces Through subjective objective evaluations, show produces videos superior quality. Moreover, can be added existing standards without altering their bitstream format.