A Neural Network-based Interframe Prediction for HEVC

A Neural Network-based Interframe Prediction for HEVC

© 2022 by IJETT Journal
Volume-70 Issue-1
Year of Publication : 2022
Authors : Kanike Sreenivasulu, T V K Hanumantha Rao
DOI :  10.14445/22315381/IJETT-V70I1P223

How to Cite?

Kanike Sreenivasulu, T V K Hanumantha Rao, "A Neural Network-based Interframe Prediction for HEVC," International Journal of Engineering Trends and Technology, vol. 70, no. 3, pp. 201-211, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I1P223

Exploration of spatial and temporal redundancies in video data is one of the most important processes in video encoding procedures, contributing to the high compression capability of the H.265 architecture, one of the latest video codecs. The aim of this paper is to come up with a deep learning-based approach for the same and contrast it with the accuracy current motion vector-based prediction system.

HEVC, H.265, inter-frame, neural networks, Video Compression, LSTMs.

[1] Gary J. Sullivan, High-Efficiency Video Coding (HEVC), Algorithms and Architectures, (2014).
[2] Kusuma. H.R, Dr.Mahesh Rao, Video Compression Using Spatial and Temporal Redundancy –A Comparative Study
[3] Vishal Deep, Realization of State of the Art Intra Prediction in High-Efficiency Video Coding.
[4] Watson, Andrew. Image Compression Using the Discrete Cosine Transform. Mathematica Journal (1994).
[5] B. S. Nanda and N. Kaulgud, Effect of quantization on video compression, IEEE International Conference on Industrial Technology, IEEE ICIT `02 2 (2002) 764-768
[6] Sze, Vivienne, and DetlevMarpe, Entropy Coding in HEVC, High-Efficiency Video Coding (HEVC) (2014) 209–274.
[7] Zhang, Hao& Ma, Zhan, Fast Intra Prediction for High-Efficiency Video Coding (2012).
[8] Z. Pan, S. Kwong, Y. Zhang, J. Lei, and H. Yuan, Fast Coding Tree Unit depth decision for high-efficiency video coding, 2014 IEEE International Conference on Image Processing (ICIP), (2014).
[9] Alex Shirstinsky, Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network.
[10] An introduction to ConvLSTM, available: https://medium.com/neuronio/an-introduction-to-convlstm-55c9025563a7”
[11] SerkanSulun, Deep Learned Frame prediction for video compression.
[12] Dhanalakshmi, A., Nagarajan, G. Convolutional Neural Network-based deblocking filter for SHVC in H.265. SIViP 14
[13] How to Improve Deep Learning Model Robustness by Adding Noise, available: machinelearningmastery.com
[14] Sandra Aigner and Marco Körner. Future Gen: Anticipating the Future Frames of Video Sequences using Spatio-Temporal 3D Convolutions in Progressively Growing GANs.
[15] Color metric article: https://www.compuphase.com/cmetric.htm
[16] Jim Nilsson, Tomas Akenine-Möller, Understanding SSIM.