CNN-Based Sample Adaptive Offset Optimization in HEVC for Streaming Video

摘要

The high efficient video coding (HEVC) standard is crucial for video processing and communication. It is able to achieve about 50% bit-rate reduction with equivalent visual quality compared to H.264/AVC. In the in-loop filter part of HEVC, sample adaptive offset (SAO) is newly added in order to improve the coding efficiency as well as the subjective quality of encoded videos. In order to improve visual quality, we propose an approach by using convolutional neural networks (CNN) after de-blocking filter (DBF) to replace SAO, namely SAOCNN in this paper. Compared with SAO, the proposed SAOCNN is able to reduce the distortion of reconstructed pixels by learning residual feature. Further more, there will be no bit-rates by using the same SAOCNN model in both encoder and decoder sides. Experimental results show that our proposed approach achieves an average 2.04% BD-rate reduction as well as the average 0.12 BDPSNR increment for All intra configuration with sacrifice of encoding time rarely.