Resolution and effective bit depth (EBD) adaptation have been recently utilised in video compression to improve coding efﬁciency. This type of approach dynamically reduces spatial/temporal resolutions and effective bit depth at the encoder and restores the original video formats during decoding. In this paper, a convolutional neural networks (CNN) based EBD adaptation method is presented for perceptual video compression, in which the employed CNN models are trained using a generative adversarial network (GAN), with perception-based loss functions. This method was integrated into the HEVC HM 16.20 reference software and fully evaluated on test sequences from the JVET Common Test Conditions using the Random Access conﬁguration. The results show signiﬁcant coding gains achieved on all test sequences with an overall bit rate saving of 24.8% (Bjøntegaard Delta measurement) based on a perceptual quality metric, VMAF.
|Title of host publication||IEEE International Conference on Multimedia & Expo (ICME)|
|Publisher||Institute of Electrical and Electronics Engineers (IEEE)|
|Publication status||Accepted/In press - 6 Mar 2020|
|Event||IEEE ICME 2020 - London, United Kingdom|
Duration: 6 Jul 2020 → 10 Jul 2020
|Conference||IEEE ICME 2020|
|Period||6/07/20 → 10/07/20|
Ma, D., Zhang, F., & Bull, D. (Accepted/In press). GAN-based Effective Bit Depth Adaptation for Perceptual Video Compression. In IEEE International Conference on Multimedia & Expo (ICME) Institute of Electrical and Electronics Engineers (IEEE).