This paper presents SUVEHP (speed up of video\ud
enhancement based on human perception), a human percep-\ud
tion-based model oriented to reduce the computational time\ud
ofdigitalvideorestoration.Inparticular,twospecifichypoth-\ud
esis tests able to classify degraded frame regions are pro-\ud
posed. Classification is performed in agreement with regions\ud
visual significance in order to enable or inhibit motion com-\ud
pensated enhancement. The level of the proposed hypothesis\ud
tests is theoretically assessed. Moreover, extensive exper-\ud
imental results on video sequences affected by additive\ud
Gaussian noise show that SUVEHP speeds up some stan-\ud
dard motion compensated denoisers up to 60%, preserving\ud
or even slightly increasing both the objective and subjective\ud
visual quality of the restored sequences