Existing entropy models in learned image compression are cumbersome to generate fixed mean and variance for estimating Gaussian distributions for latent representation. In this paper, we propose a novel entropy model based on Gaussian process regression (GPR) that flexibly predicts the mean of Gaussians with posterior distributions characterized by covari-ance functions spanned in the high-dimensional feature space. Furthermore, we develop the rate-distortion optimization based on the proposed entropy model by approximating the bitrates with the evidence lower bound (ELBO) derived via variational inference for GPR. The proposed model can be seamlessly integrated into existing end-to-end optimized frame-works by substituting the masked convolution based autoregressive models. Experimental results demonstrate that the proposed model outperforms conventional image compression methods such as JPEG2000 and BPG, as well as recent learning based methods on the Kodak dataset in terms of rate-distortion performance.

Summary form only given. Screen content videos increasingly gain the popularity due to the rapid advances in cloud and multimedia technologies, which in turn requires highly efficient screen content compression. A recent standard, namely SCC is under development in JCT-VC, Joint Collaborative Team on Video Coding between ISO/IEC and ITU-T. In SCC, the most efficient new coding tool is Intra block copy (Intra BC). In this paper, we describe the Intra BC that has been proposed by the authors and adopted in the SCC standard and reference software for coding of screen content. Different from the conventional Intra prediction method where the prediction signal is derived from the spatially neighboring samples, the Intra BC mode greatly improves the prediction efficiency by fully exploiting the redundancy of repetitive patterns which typically appear in screen content. Experimental results suggest that the Intra BC mode can improve the coding efficiency significantly for typical screen content video sequences with 43.2% bit rate reduction on average.

This article provides an overview of standardized extensions of HEVC for the advanced coding of 3D and multiview video. In those extensions, new coding tools that better exploit the inter-view redundancy of the multiview texture videos have been developed. Additionally, dedicated tools for the improved coding of depth have been extensively studied and incorporated into the standard. In this paper, the performance of these extensions is assessed, and experimental results demonstrate notable gains in coding efficiency.

This paper describes a scalable video codec that was submitted as a response to the joint call for proposals issued by ISO/IEC MPEG and ITU-T VCEG on HEVC scalable extension. The proposed codec uses a multi-loop decoding structure. Several inter-layer texture prediction methods are employed to remove the inter-layer redundancy. Inter-layer prediction is also used when coding enhancement layer syntax elements such as motion parameter and intra prediction mode, to further reduce bit overhead. Additionally, alternative transforms as well as adaptive coefficients scanning are used to code the prediction residues more efficiently. Experimental results are presented to demonstrate the effectiveness of the proposed scheme. When compared to HEVC single-layer coding, the additional rate overhead for the proposed scalable extension is 1.2% to 6.4% to achieve two layers of SNR and spatial scalability.