Early SKIP Mode Decision Method in HEVC Based on Perceptual Distortion Measure

Abstract

An effective fast SKIP mode decision method is proposed for the High Efficiency Video Coding (HEVC) encoding. In order to determine the best Prediction Unit (PU) mode for a given Coding Unit (CU), the reference software for HEVC checks every PU mode candidate. This causes enormous computational complexity, especially in HEVC inter coding, which should be tackled for a fast encoder. An algorithm is proposed which exploits the fact that the SKIP mode can be directly decided as an optimal PU mode when reconstructed CUs of all candidates are similar. This is because bits for the SKIP mode is pretty small compared to other candidates. Thus, the distortion value between reconstructed CUs in $2\mathrm{N} \times 2\mathrm{N}$ Merge and SKIP mode is measured in terms of the Human Visual System (HVS). If it is determined as unnoticeable, then a given CU is encoded in the SKIP mode. Experimental results show that the proposed method can save encoding time by 48.11 % and 41.66 % on average with minor objective quality losses under the Random Access (RA) and Low Delay (LD)-B configurations respectively.