Tien-Yang Hsu, Yu Lu, Tung-Hung Hsieh, Chou-Chen Wang
{"title":"An Efficient HEVC Intra Frame Coding Based on Deep Convolutional Neural Network","authors":"Tien-Yang Hsu, Yu Lu, Tung-Hung Hsieh, Chou-Chen Wang","doi":"10.1109/SNPD51163.2021.9704928","DOIUrl":null,"url":null,"abstract":"High efficiency video coding (HEVC) is a very popular video coding standard. The HEVC can achieve high coding efficiency with a lower bitrate for intra frame coding. However, it still needs many bits to finish best rate-distortion (R-D) curve. Since there are only 35 directions prediction modes provided in intra prediction module (IPM), HEVC occurs a large distortion when the image contents are out of these prediction directions. In order to obtain a better R-D curve, Zhang et al. [3] recently proposed a simple convolutional neural network (S-CNN) to improve the encoding performance of HEVC. However, S-CNN has to consume more time to encode intra frame coding since it needs to perform more CNN enhancement mode. In order to further speed up S-CNN based intra frame coding, we propose an early termination algorithm to skip CNN. Because the natural images are generally homogenous, we find the mean square errors (MSE) of reconstructed CTU exist high spatial correlation at HEVC encoder. Therefore, a dynamic threshold of MSE is set according to three neighboring encoded CTU blocks to evaluate whether the current reconstructed CTU is useful for the CNN enhancement mode. Simulation results show that the proposed method can achieve faster HEVC encoding process than S-CNN by reducing time increase ratio (TIR) about 12% on an average.","PeriodicalId":235370,"journal":{"name":"2021 IEEE/ACIS 22nd International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE/ACIS 22nd International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SNPD51163.2021.9704928","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
High efficiency video coding (HEVC) is a very popular video coding standard. The HEVC can achieve high coding efficiency with a lower bitrate for intra frame coding. However, it still needs many bits to finish best rate-distortion (R-D) curve. Since there are only 35 directions prediction modes provided in intra prediction module (IPM), HEVC occurs a large distortion when the image contents are out of these prediction directions. In order to obtain a better R-D curve, Zhang et al. [3] recently proposed a simple convolutional neural network (S-CNN) to improve the encoding performance of HEVC. However, S-CNN has to consume more time to encode intra frame coding since it needs to perform more CNN enhancement mode. In order to further speed up S-CNN based intra frame coding, we propose an early termination algorithm to skip CNN. Because the natural images are generally homogenous, we find the mean square errors (MSE) of reconstructed CTU exist high spatial correlation at HEVC encoder. Therefore, a dynamic threshold of MSE is set according to three neighboring encoded CTU blocks to evaluate whether the current reconstructed CTU is useful for the CNN enhancement mode. Simulation results show that the proposed method can achieve faster HEVC encoding process than S-CNN by reducing time increase ratio (TIR) about 12% on an average.