Enhancing HEVC Compressed Videos with a Partition-masked Convolutional Neural Network

10 May 2018  ·  Xiaoyi He, Qiang Hu, Xintong Han, Xiaoyun Zhang, Chongyang Zhang, Weiyao Lin ·

In this paper, we propose a partition-masked Convolution Neural Network (CNN) to achieve compressed-video enhancement for the state-of-the-art coding standard, High Efficiency Video Coding (HECV). More precisely, our method utilizes the partition information produced by the encoder to guide the quality enhancement process... In contrast to existing CNN-based approaches, which only take the decoded frame as the input to the CNN, the proposed approach considers the coding unit (CU) size information and combines it with the distorted decoded frame such that the degradation introduced by HEVC is reduced more efficiently. Experimental results show that our approach leads to over 9.76% BD-rate saving on benchmark sequences, which achieves the state-of-the-art performance. read more

PDF Abstract
No code implementations yet. Submit your code now




  Add Datasets introduced or used in this paper