Optimizing Video Coding Using Neural Networks: A Comprehensive Review of Methods and Applications

Riki, Mehran; Mohammadi, Fateme; Khazeni, Pouria

doi:10.22034/apj.2025.725730

Optimizing Video Coding Using Neural Networks: A Comprehensive Review of Methods and Applications

Document Type : Review Paper

Authors

Mehran Riki ¹

Fateme Mohammadi ²

Pouria Khazeni ³

¹ 1*Department of Computer Engineering, National University of Skill(NUS), Tehran, Iran

² Faculty of Mathematics, Statistics, and Computer Science, University of Sistan and Baluchestan, Zahedan, Iran

³ Faculty of Management and Economics, University of Sistan and Baluchestan, Zahedan, Iran

10.22034/apj.2025.725730

Abstract

With the rising demand for high-quality video services such as live streaming, virtual reality, and UHD videos, efficient video coding methods have become increasingly critical. Standards like H.264, H.265, and H.266 aim to reduce data volume while preserving image quality, yet they face challenges such as computational complexity, bandwidth management, and compression resilience. This paper provides a comprehensive review of neural network-based approaches for optimizing video coding. The reviewed methods include convolutional neural networks (CNNs) for intra-mode prediction, LSTM and Seq2Seq models for video traffic modeling, and inverse neural networks (INNs) for robust video hiding. Findings indicate that these techniques can reduce encoding time by up to 70%, enhance frame size prediction accuracy to 13.6%, and improve the resilience of stego videos against compression. Practical applications in bandwidth management, coding optimization for resource-constrained devices, and video security are explored. This study underscores the significant potential of deep learning in advancing video coding standards and suggests future research directions.

Keywords

Video coding

Neural networks

Optimization

[1] Lin, T.-L., et al. (2023). Intra mode prediction for H.266/FVC video coding based on convolutional neural network. IEEE Transactions on Circuits and Systems for Video Technology, 33(2), 123-135.

[2] Om, K., et al. (2023). H.264 and H.265 video traffic modeling using neural networks. IEEE Transactions on Multimedia, 25(4), 567-579.

[3] Shen, X., et al. (2023). VHNet: A Video Hiding Network with robustness to video coding. IEEE Access, 11, 3456-3470.

[4] Liu, C. (2023). Fast HEVC inter-frame coding based on LSTM neural network technology. IEEE Transactions on Image Processing, 32, 2345-2358.

[5] Cao, X., et al. (2023). Fast intra coding in AVS3 based on direct non-first pre-coding skip. IEEE Transactions on Multimedia, 25(5), 678-690.

[6] Kim, J., et al. (2022). Deep learning for video coding: A comprehensive review. IEEE Signal Processing Magazine, 39(1), 78-91.

[7] Patel, R., & Gupta, A. (2023). Neural network approaches to video compression: Trends and challenges. Journal of Visual Communication and Image Representation, 85, 102-115.

[8] Zhang, Y., et al. (2023). A CNN-based approach to optimize intra prediction for video coding. IEEE Access, 11, 4123-4135.

[9] Wu, H., et al. (2022). Enhancing video coding efficiency using deep learning techniques. Journal of Electronic Imaging, 31(3), 033012.

[10] Wang, L., et al. (2023). Integration of LSTM networks in H.265 video coding for improved rate-distortion performance. IEEE Transactions on Circuits and Systems for Video Technology, 33(3), 456-468.

[11] Rodriguez, M., et al. (2023). Adaptive video coding using Seq2Seq models: A performance evaluation. Multimedia Tools and Applications, 82(4), 599-612.

[12] Singh, P., & Kumar, S. (2023). Optimization of video coding for mobile devices using deep neural networks. IEEE Mobile Computing, 22(2), 88-101.

[13] Hernandez, R., et al. (2023). Video compression and quality enhancement via deep learning methods. IEEE Transactions on Consumer Electronics, 69(1), 45-57.

[14] Lee, D., et al. (2023). Recent advances in neural network-based video coding: A survey. ACM Computing Surveys, 55(6), 1-34.

[15] Chen, Y., et al. (2023). Robust video coding under compression artifacts using inverse neural networks. IEEE Access, 11, 5678-5690.

[16] Garcia, L., et al. (2023). Improving video streaming quality with deep learning-based bandwidth management. IEEE Transactions on Broadcasting, 69(2), 112-125.

[17] Martinez, F., et al. (2023). Efficient video coding for 4K and 8K content using hybrid neural network models. Journal of Multimedia, 17(3), 234-247.

[18] Ahmed, S., et al. (2022). Edge computing and neural networks for real-time video encoding. IEEE Internet of Things Journal, 9(4), 3456-3468.

[19] Patel, D., et al. (2023). Neural network assisted video coding for low-latency applications. IEEE Transactions on Multimedia, 25(6), 789-801.

[20] Zhang, Q., et al. (2023). Transformer-based architectures in next-generation video coding. IEEE Transactions on Circuits and Systems for Video Technology, 33(4), 789-803.