Predicting Rate Control Target Through A Learning Based Content Adaptive Model

Rate Control (RC) plays an important role in video encoding. Traditional solutions are using fixed rate or fixed quantization parameters as the unified rate-control targets for all videos in one given video application. However, unified ratecontrol targets tend to have some bad encoding cases because of applying wrong rate for the video content. In this paper, we propose one content-adaptive rate control solution. We employ one neural-network based model which can end-to-end learn the optimal rate-control target appropriate to the content characteristics. The experimental results show that the proposed model can predict the optimal rate-factor value with the accuracy up to 77.637%. With this model, the proposed video-encoding method can significantly decrease the encoding quality fluctuation.