Mohsen Abdoli

Yiqun Liu, Mohsen Abdoli, Thomas Guionnet et al.

The Versatile Video Coding (VVC) standard has been finalized by Joint Video Exploration Team (JVET) in 2020. Compared to the High Efficiency Video Coding (HEVC) standard, VVC offers about 50% compression efficiency gain, in terms of Bjontegaard Delta-Rate (BD-rate), at the cost of about 10x more encoder complexity. In this paper, we propose a Convolutional Neural Network (CNN)-based method to speed up inter partitioning in VVC. Our method operates at the Coding Tree Unit (CTU) level, by splitting each CTU into a fixed grid of 8x8 blocks. Then each cell in this grid is associated with information about the partitioning depth within that area. A lightweight network for predicting this grid is employed during the rate-distortion optimization to limit the Quaternary Tree (QT)-split search and avoid partitions that are unlikely to be selected. Experiments show that the proposed method can achieve acceleration ranging from 17% to 30% in the RandomAccess Group Of Picture 32 (RAGOP32) mode of VVC Test Model (VTM)10 with a reasonable efficiency drop ranging from 0.37% to 1.18% in terms of BD-rate increase.

Mohsen Abdoli, Félix Henry, Patric Brault et al.

A few years after standardization of the High Efficiency Video Coding (HEVC), now the Joint Video Exploration Team (JVET) group is exploring post-HEVC video compression technologies. In the intra prediction domain, this effort has resulted in an algorithm with 67 internal modes, new filters and tools which significantly improve HEVC. However, the improved algorithm still suffers from the long distance prediction inaccuracy problem. In this paper, we propose an In-Loop Residual coding Intra Prediction (ILR-IP) algorithm which utilizes inner-block reconstructed pixels as references to reduce the distance from predicted pixels. This is done by using the ILR signal for partially reconstructing each pixel, right after its prediction and before its block-level out-loop residual calculation. The ILR signal is decided in the rate-distortion sense, by a brute-force search on a QP-dependent finite codebook that is known to the decoder. Experiments show that the proposed ILR-IP algorithm improves the existing method in the Joint Exploration Model (JEM) up to 0.45% in terms of bit rate saving, without complexity overhead at the decoder side.

Mohsen Abdoli, Hossein Sarikhani, Mohammad Ghanbari et al.

In this paper, a method for enhancing low contrast images is proposed. This method, called Gaussian Mixture Model based Contrast Enhancement (GMMCE), brings into play the Gaussian mixture modeling of histograms to model the content of the images. Based on the fact that each homogeneous area in natural images has a Gaussian-shaped histogram, it decomposes the narrow histogram of low contrast images into a set of scaled and shifted Gaussians. The individual histograms are then stretched by increasing their variance parameters, and are diffused on the entire histogram by scattering their mean parameters, to build a broad version of the histogram. The number of Gaussians as well as their parameters are optimized to set up a GMM with lowest approximation error and highest similarity to the original histogram. Compared to the existing histogram-based methods, the experimental results show that the quality of GMMCE enhanced pictures are mostly consistent and outperform other benchmark methods. Additionally, the computational complexity analysis show that GMMCE is a low complexity method.