Two-Step Predictive Models for Low-Complexity Multiple Transform Selection in VVC

• Caroline Camargo UFPel https://orcid.org/0000-0002-7563-4556
• Daniel Palomino UFPel https://orcid.org/0000-0003-0409-8335
• Guilherme Correa UFPel https://orcid.org/0000-0002-2739-6194

DOI: https://doi.org/10.5753/semish.2026.22582

Resumo

The Versatile Video Coding (VVC) standard achieves high compression efficiency but with significantly increased computational complexity. A major contributor is the Multiple Transform Selection (MTS) process, which exhaustively evaluates multiple transform combinations. This work proposes a machine learning approach using lightweight decision trees to replace the exhaustive MTS search. The models are trained with balanced sampling, feature selection, and hyperparameter optimization. Experiments in the All Intra configuration show an average encoding time reduction of 18.76% with only a 0.67% increase in BD-rate, reaching up to 30.90% time savings in the transform stage.

Referências

Bjøntegaard, G. (2001). Calculation of average psnr differences between rd-curves.

Bossen, F. VTM common test conditions and software reference configuration for SDR video. [link].

Camargo, C., Silveira, B., and Correa, G. (2025a). Computational cost analysis and reduction of vvc multiple transform selection. In 2025 IEEE 16th Latin America Symposium on Circuits and Systems (LASCAS), volume 1, pages 1–5.

Camargo, C., Silveira, B., Zatt, B., and Correa, G. (2025b). Machine learning-driven multiple transform selection for low-complexity vvc encoding. In 2025 IEEE International Symposium on Circuits and Systems (ISCAS), pages 1–5.

Camargo, C. S., Silveira, B., and Correa, G. (2025c). A comprehensive analysis of the multiple transform selection tool in versatile video coding. Journal of Integrated Circuits and Systems, 20(2).

Fraunhofer (2020). Fraunhofer hhi is proud to present the new state-of-the-art in global video coding: H.266/VVC brings video transmission to new speed. [link].

Hamidouche, W., Biatek, T., Abdoli, M., François, F., Radosavljević, M., Menard, D., and Raulet, M. (2022). Versatile video coding standard: A review from coding tools to consumers deployment. IEEE Consumer Electronics Magazine, 11(5):10–24.

JVET (2024). VVC software VTM, VTM-23.0. Pakdaman, F., Adelimanesh, M. A., Gabbouj, M., and Hashemi, M. R. (2020). Complexity analysis of next-generation VVC encoding and decoding. In 2020 IEEE International Conference on Image Processing (ICIP), pages 3134–3138.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in python. J. Mach. Learn. Res., 12(null):2825–2830.

Saldanha, M., Sanchez, G., Marcon, C., and Agostini, L. (2022). Fast transform decision scheme for VVC intra-frame prediction using decision trees. In 2022 IEEE International Symposium on Circuits and Systems (ISCAS), pages 1948–1952.

Samir, S., Damak, T., Saumard, M., Ben Ayed, M. A., Jridi, M., and Masmoudi, N. (2024a). Performance analysis of mts on the vvc encoder. Signal, Image and Video Processing, 18(2):1671–1681.

Samir, S., Saumard, M., Damak, T., Jridi, M., and Ben Ayed, M. A. (2024b). Random forest based fast mts algorithm for vvc encoder. In International Conference on Service-Oriented Computing, pages 287–298. Springer.

Siqueira, Í., Correa, G., and Grellert, M. (2020). Rate-distortion and complexity comparison of hevc and vvc video encoders. In 2020 IEEE 11th Latin American Symposium on Circuits & Systems (LASCAS), pages 1–4. IEEE.

Vitter, J. S. (1985). Random sampling with a reservoir. ACM Trans. Math. Softw., 11(1). Wang, Z., Wang, J., Yang, J., Luo, C., Liang, F., and Huang, K. (2022). A fast transform algorithm for VVC intra coding. In 2022 11th International Conference on Communications, Circuits and Systems (ICCCAS), pages 237–240.

Zhao, X., Chen, J., Choi, K., Cock, J. D., Grange, A., He, Y., Helle, P., Ye, Y., and Zhang, L. AOM common test conditions v2.0. [link].

Zhao, X., Kim, S.-H., Zhao, Y., Egilmez, H. E., Koo, M., Liu, S., Lainema, J., and Karczewicz, M. (2021). Transform Coding in the VVC Standard. IEEE Transactions on Circuits and Systems for Video Technology, 31(10):3878–3890.