Fast VVC Angular Intra-Prediction for 360° Videos Based on Decision Trees

  • Ramiro Viana UFPel
  • Iago Storch UFPel
  • Rogério Rosado UFPel
  • Marcelo Porto UFPel
  • Guilherme Corrêa UFPel
  • Luciano Agostini UFPel

Resumo


The rapid growth of immersive media has positioned 360° videos as a key component in applications such as virtual reality, remote education, tourism, and interactive entertainment. But the massive data volume required to represent 360° videos imposes significant computational challenges to deliver this type of content across the high diversity of current and future devices with support for multimedia. Then, highly efficient video encoding algorithms are required in this scenario. Versatile Video Coding (VVC) is the current state-of-the-art standard for video compression, offering specialized tools for efficient 360° video coding. This paper introduces a Machine Learning-based approach to reduce the computational effort of VVC Angular Intra-Prediction (AIP) tool when encoding 360° video content. The proposed method uses a Decision Tree model to adaptively skip vertical prediction modes in the AIP process. Experimental results show an average encoding time reduction of 10.11% with only a 0.66% impact on coding efficiency. To the best of our knowledge, this is the first work to explore the use of Machine Learning to reduce the computational effort of AIP for 360° videos.

Palavras-chave: 360° videos, VVC, Angular Intra-Prediction, Machine Learning

Referências

Larissa Araújo, Adson Duarte, Bruno Zatt, Guilherme Correa, and Daniel Palomino. 2024. Fast ISP Mode Decision for the Versatile Video Coding Intra Prediction Using Machine Learning. In Proceedings of the 30th Brazilian Symposium on Multimedia and the Web (Juiz de Fora/MG). SBC, Porto Alegre, RS, Brasil, 162–170. DOI: 10.5753/webmedia.2024.241692

BayesWitnesses. 2022. m2cgen: Model 2 Code Generator. [link]. Acessado em: 11 ago. 2025.

Bernardo Beling, Iago Storch, Luciano Agostini, Bruno Zatt, Sergio Bampi, and Daniel Palomino. 2020. ERP-Based CTU Splitting Early Termination for Intra Prediction of 360 videos. In 2020 IEEE International Conference on Visual Communications and Image Processing (VCIP). 359–362. DOI: 10.1109/VCIP49819.2020.9301879

James Bergstra and Yoshua Bengio. 2012. Random search for hyper-parameter optimization. The Journal of Machine Learning Research 13 (2012), 281–305.

Gisle Bjontegaard. 2001. Calculation of average PSNR differences between RDcurves. Technical Report VCEG-M33, ITU-TSG16/Q6, Austin, Texas, USA.

Vinicius Borges, Murilo Perleberg, Marcelo Porto, and Luciano Agostini. 2024. High-Throughput Hardware Design for the Complete VVC Angular Intra Prediction. In 2024 31st IEEE International Conference on Electronics, Circuits and Systems (ICECS). 1–5. DOI: 10.1109/ICECS61496.2024.10848892

Vinicius Borges, Murilo Perleberg, Marcelo Porto, and Luciano Agostini. 2025. Hardware Design for VVC Angular Intra Prediction Modes with Coding Efficiency Awareness. In 2025 IEEE 16th Latin America Symposium on Circuits and Systems (LASCAS), Vol. 1. 1–5. DOI: 10.1109/LASCAS64004.2025.10966271

Jill Boyce, Elena Alshina, Adeel Abbas, and Yan Ye. 2018. JVET common test conditions and evaluation procedures for 360° video. JVET output document JVETJ1012. Joint Video Exploration Team (JVET), ITU-T SG16 WP3 and ISO/IEC JTC1/SC29/WG11, Chengdu, China. [link] Presented at the 4th JVET meeting, Chengdu, China, October 15–21, 2016.

Benjamin Bross, Ye-Kui Wang, Yan Ye, Shan Liu, Jianle Chen, Gary J. Sullivan, and Jens-Rainer Ohm. 2021. Overview of the Versatile Video Coding (VVC) Standard and its Applications. IEEE Transactions on Circuits and Systems for Video Technology 31, 10 (2021), 3736–3764. DOI: 10.1109/TCSVT.2021.3101953

Adrian Browne, Yan Ye, and Seung Hwan Kim. 2022. Algorithm description for Versatile Video Coding and Test Model 19 (VTM 19). Jt. Video Expert. Team ITU-T SG 16 WP 3 ISO/IEC JTC 1/SC 29, 26th Meet. by teleconference (April 2022).

Bolin Chen, Zhao Wang, Binzhe Li, Shiqi Wang, and Yan Ye. 2023. Compact Temporal Trajectory Representation for Talking Face Video Compression. IEEE Transactions on Circuits and Systems for Video Technology (2023), 1–14. DOI: 10.1109/TCSVT.2023.3271130

Yan Chen, Tiansong Li, Haokun Liu, Shaoguo Cui, Li Yu, KejunWu, and Hongkui Wang. 2024. A fast intra CU partition algorithm in Versatile Video Coding for 360-degree video. Journal of Visual Communication and Image Representation 104 (2024), 104305. DOI: 10.1016/j.jvcir.2024.104305

Yamei Chen, Li Yu, Hongkui Wang, Tiansong Li, and Shengwei Wang. 2020. A novel fast intra mode decision for versatile video coding. Journal of Visual Communication and Image Representation 71 (2020), 102849. DOI: 10.1016/j.jvcir.2020.102849

Ramatoulaye Diallo, Codjo Edalo, and O Olawale Awe. 2024. Machine Learning Evaluation of Imbalanced Health Data: A Comparative Analysis of Balanced Accuracy, MCC, and F1 Score. In Practical Statistical Learning and Data Science Methods: Case Studies from LISA 2020 Global Network, USA. Springer, 283–312.

Adson Duarte, Bruno Zatt, Guilherme Correa, and Daniel Palomino. 2023. Fast Intra Mode Decision Using Machine Learning for the Versatile Video Coding Standard. In 2023 IEEE International Symposium on Circuits and Systems (ISCAS). 1–5. DOI: 10.1109/ISCAS46773.2023.10181769

Jose N. Filipe, J. Carreira, Luis M. N. Tavora, Sergio M. M. de Faria, Antonio Navarro, and Pedro A. A. Assuncao. 2021. Tree-Based Ensemble Methods for Complexity Reduction of VVC Intra Coding. In 2021 Telecoms Conference (ConfTELE). 1–6. DOI: 10.1109/ConfTELE50222.2021.9435476

Jose N. Filipe, Luis M. N. Tavora, Sergio M. M. Faria, Antonio Navarro, and Pedro A. A. Assuncao. 2025. Linear Multivariate Decision Trees for Fast QTMT Partitioning in VVC. IEEE Open Journal of Signal Processing 6 (2025), 175–183. DOI: 10.1109/OJSP.2025.3528897

Fraunhofer Heinrich Hertz Institute (HHI) Joint Video Experts Team (JVET). 2022. VTM reference software for VVC version 19.0. [link].

Xu Liu, Yongcheng Huang, Li Song, Rong Xie, and Xiaokang Yang. 2017. The SJTU UHD 360-Degree Immersive Video Sequence Dataset. In 2017 International Conference on Virtual Reality and Visualization (ICVRV). IEEE, 400–401. DOI: 10.1109/ICVRV.2017.00095

Samir Marwaha. 2024. Sandvine’s 2024 Global Internet Phenomena Report: Global Internet Usage Continues to Grow. [link]

Rogério Rosado, Otávio Santos, Franklin de Oliveira, Lucas Silva, Vanessa Aldrighi, Iago Storch, Gustavo Sanchez, Daniel Palomino, and Luciano Agostini. 2025. Fast Heuristic for VVC Intra-frame Prediction Targeting 360° Video Formats. In 2025 IEEE 16th Latin America Symposium on Circuits and Systems (LASCAS), Vol. 1. 1–5. DOI: 10.1109/LASCAS64004.2025.10966322

Rogério Rosado, Otávio Santos, Franklin Oliveira, Lucas Silva, Gustavo Sanchez, Iago Storch, Daniel Palomino, and Luciano Agostini. 2024. A Coding-Efficiency-Aware Fast Heuristic for VVC Intra-Frame Prediction Targeting 360° Videos. In Proceedings of the 30th Brazilian Symposium on Multimedia and the Web (Juiz de Fora/MG). SBC, Porto Alegre, RS, Brasil, 355–359. DOI: 10.5753/webmedia.2024.243128

Mário Saldanha, Gustavo Sanchez, César Marcon, and Luciano Agostini. 2021. Performance analysis of VVC intra coding. Journal of Visual Communication and Image Representation 79 (2021), 103202. DOI: 10.1016/j.jvcir.2021.103202

Icaro Siqueira, Guilherme Correa, and Mateus Grellert. 2020. Rate-Distortion and Complexity Comparison of HEVC and VVC Video Encoders. In 2020 IEEE 11th Latin American Symposium on Circuits and Systems (LASCAS). 1–4. DOI: 10.1109/LASCAS45839.2020.9069036

Iago Storch, Luciano Agostini, Bruno Zatt, Sergio Bampi, and Daniel Palomino. 2022. FastInter360: A Fast Inter Mode Decision for HEVC 360 Video Coding. IEEE Transactions on Circuits and Systems for Video Technology 32, 5 (2022), 3235–3249. DOI: 10.1109/TCSVT.2021.3096752

Iago Storch, Luciano Agostini, Bruno Zatt, and Daniel Palomino. 2021. Exploring ERP Distortions to Reduce the Encoding Time of 360 Videos. In Anais Estendidos da XXXIV Conference on Graphics, Patterns and Images (Online). SBC, Porto Alegre, RS, Brasil, 139–145. DOI: 10.5753/sibgrapi.est.2021.20026

G.J. Sullivan and T. Wiegand. 1998. Rate-distortion optimization for video compression. IEEE Signal Processing Magazine 15, 6 (1998), 74–90. DOI: 10.1109/79.733497

Ei Ei Tun, Supavadee Aramvith, and Takao Onoye. 2022. Low complexity mode selection for H.266/VVC intra coding. ICT Express 8, 1 (2022), 83–90. DOI: 10.1016/j.icte.2021.08.018

Mai Xu, Chen Li, Shanyi Zhang, and Patrick Le Callet. 2020. State-of-the-Art in 360° Video/Image Processing: Perception, Assessment and Compression. IEEE Journal of Selected Topics in Signal Processing 14, 1 (2020), 5–26. DOI: 10.1109/JSTSP.2020.2966864

Mengmeng Zhang, Yan Hou, and Zhi Liu. 2023. An early CU partition mode decision algorithm in VVC based on variogram for virtual reality 360 degree videos. EURASIP Journal on Image and Video Processing 2023, 1 (2023), 9.

Wenjun Zheng, Chao Yang, Ping An, Xinpeng Huang, and Liquan Shen. 2024. Learning-based CU partition prediction for fast panoramic video intra coding. Expert Systems with Applications 258 (2024), 125187. DOI: 10.1016/j.eswa.2024.125187
Publicado
10/11/2025
VIANA, Ramiro; STORCH, Iago; ROSADO, Rogério; PORTO, Marcelo; CORRÊA, Guilherme; AGOSTINI, Luciano. Fast VVC Angular Intra-Prediction for 360° Videos Based on Decision Trees. In: BRAZILIAN SYMPOSIUM ON MULTIMEDIA AND THE WEB (WEBMEDIA), 31. , 2025, Rio de Janeiro/RJ. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2025 . p. 550-554. DOI: https://doi.org/10.5753/webmedia.2025.16075.

Artigos mais lidos do(s) mesmo(s) autor(es)

1 2 > >>