Saliency-Guided Complexity Control for HEVC Decoding

The latest High Efficiency Video Coding (HEVC) standard significantly improves coding efficiency over its previous video coding standards. The expense of such improvement is enormous computational complexity, from both encoding and decoding sides. Since computational capability and power capacity are diverse across portable devices, it is necessary to reduce decoding complexity to a target with tolerable quality loss, so called complexity control. This paper proposes a SaliencyGuided Complexity Control (SGCC) approach for HEVC decoding, which reduces the decoding complexity to the target with minimal perceptual quality loss. First, an HEVC domain method is developed to detect video saliency from HEVC bitstreams, as the preliminary for assessing perceptual quality. Based on detected saliency, we establish the SGCC formulation to minimize perceptual quality loss at the constraint on reduced decoding complexity, which is achieved via disabling Deblocking Filter (DF) and simplifying Motion Compensation (MC) of some nonsalient Coding Tree Units (CTUs). One important component in this formulation is the modelled relationship between decoding complexity reduction and DF disabling/MC simplification, which determines the control accuracy of our approach. Another component is the modelled relationship between quality loss and DF disabling/MC simplification, responsible for optimizing perceptual quality. By solving the SGCC formulation, we can obtain the DF and MC states of each CTU given a target complexity, and then decoding complexity can be reduced to the target. Finally, the experimental results validate the effectiveness of our SGCC approach, from the aspects of control performance, complexity-distortion performance, fluctuation of quality loss and subjective quality.