Review: CNNAC TCSVT’19 —Convolutional Neural Network-Based Arithmetic Coding (HEVC Intra)

Using DenseNet Blocks, 4.7% Average BD-Rate Reduction, Up to 6.7% BD-Rate Reduction

In this story, Convolutional Neural Network-Based Arithmetic Coding (CNNAC), by University of Science and Technology of China, Microsoft Research Asia, and University of Missouri-Kansas City, is briefly presented. I read this because I work on video coding research. In

  • In this paper, CNNAC is extended to encode AC coefficients as well.

Outline

  1. CNNAC: Overall Scheme
  2. CNNAC: Network Architecture
  3. Experimental Results

1. CNNAC: Overall Scheme

CNNAC: Overall Scheme
  • For LastXY syntax element (SE), no other inputs since it is the first SE to be coded.
  • For DC and AC, the current reconstructed block generated with the encoded coefficients are also used as input.
  • Only SEs whose percentages of bits exceeds 3.0% are considered to use CNNAC. This includes LastXY, DC, AC1, AC2, AC3, AC4 and AC5.
  • Other SEs only use the conventional CABAC in HEVC.

2. CNNAC: Network Architecture

  • Standard DenseNet is used as shown in the above figure.
  • But different SE has different DenseNet structure.
  • For TU sizes 4×4, 8×8, 16×16, and 32×32, the layer number in DenseNet is 27, 40, 53, and 66, including 2, 3, 4, and 5 dense blocks, respectively.
  • In each dense block, 12 layers are included.

3. Experimental Results

3.1. BD-Rate

BD-Rate (%) on HEVC Test Sequences
BD-Rate (%) on HEVC Test Sequences

3.2. RD Curves

RD Curves

3.3. Computational Complexity

Computational Complexity
Computational Complexity

PhD, Researcher. I share what I've learnt and done. :) My LinkedIn: https://www.linkedin.com/in/sh-tsang/, My Paper Reading List: https://bit.ly/33TDhxG