Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
167 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Adaptive Online Learning of Separable Path Graph Transforms for Intra-prediction (2402.16371v1)

Published 26 Feb 2024 in eess.IV

Abstract: Current video coding standards, including H.264/AVC, HEVC, and VVC, employ discrete cosine transform (DCT), discrete sine transform (DST), and secondary to Karhunen-Loeve transforms (KLTs) decorrelate the intra-prediction residuals. However, the efficiency of these transforms in decorrelation can be limited when the signal has a non-smooth and non-periodic structure, such as those occurring in textures with intricate patterns. This paper introduces a novel adaptive separable path graph-based transform (GBT) that can provide better decorrelation than the DCT for intra-predicted texture data. The proposed GBT is learned in an online scenario with sequential K-means clustering, which groups similar blocks during encoding and decoding to adaptively learn the GBT for the current block from previously reconstructed areas with similar characteristics. A signaling overhead is added to the bitstream of each coding block to indicate the usage of the proposed graph-based transform. We assess the performance of this method combined with H.264/AVC intra-coding tools and demonstrate that it can significantly outperform H.264/AVC DCT for intra-predicted texture data.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (23)
  1. T. Wiegand, G. J. Sullivan, G. Bjontegaard, and A. Luthra, “Overview of the h. 264/avc video coding standard,” IEEE Transactions on circuits and systems for video technology, vol. 13, no. 7, pp. 560–576, 2003.
  2. G. J. Sullivan, J.-R. Ohm, W.-J. Han, and T. Wiegand, “Overview of the high efficiency video coding (hevc) standard,” IEEE Transactions on circuits and systems for video technology, vol. 22, no. 12, pp. 1649–1668, 2012.
  3. B. Bross, Y.-K. Wang, Y. Ye, S. Liu, J. Chen, G. J. Sullivan, and J.-R. Ohm, “Overview of the versatile video coding (vvc) standard and its applications,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 10, pp. 3736–3764, 2021.
  4. G. Strang, “The discrete cosine transform,” SIAM review, vol. 41, no. 1, pp. 135–147, 1999.
  5. X. Zhao, S.-H. Kim, Y. Zhao, H. E. Egilmez, M. Koo, S. Liu, J. Lainema, and M. Karczewicz, “Transform coding in the vvc standard,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 10, pp. 3878–3890, 2021.
  6. Y. Ye and M. Karczewicz, “Improved h. 264 intra coding based on bi-directional intra prediction, directional transform, and adaptive coefficient scanning,” in 2008 15th IEEE International Conference on Image Processing.   IEEE, 2008, pp. 2116–2119.
  7. S. Takamura and A. Shimizu, “On intra coding using mode dependent 2d-klt,” in 2013 Picture Coding Symposium (PCS).   IEEE, 2013, pp. 137–140.
  8. Y. Liu and J. Ostermann, “Scene-based klt for intra coding in hevc,” in 2018 Picture Coding Symposium (PCS).   IEEE, 2018, pp. 6–10.
  9. C. Lan, J. Xu, G. Shi, and F. Wu, “Exploiting non-local correlation via signal-dependent transform (sdt),” IEEE Journal of Selected Topics in Signal Processing, vol. 5, no. 7, pp. 1298–1308, 2011.
  10. D. I. Shuman, S. K. Narang, P. Frossard, A. Ortega, and P. Vandergheynst, “The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains,” IEEE signal processing magazine, vol. 30, no. 3, pp. 83–98, 2013.
  11. A. Ortega, P. Frossard, J. Kovačevic´´c{\acute{\text{c}}}over´ start_ARG c end_ARG, J. M. Moura, and P. Vandergheynst, “Graph signal processing: Overview, challenges, and applications,” Proceedings of the IEEE, vol. 106, no. 5, pp. 808–828, 2018.
  12. H. E. Egilmez, E. Pavez, and A. Ortega, “Graph learning from data under laplacian and structural constraints,” IEEE Journal of Selected Topics in Signal Processing, vol. 11, no. 6, pp. 825–841, 2017.
  13. E. Pavez, H. E. Egilmez, and A. Ortega, “Learning graphs with monotone topology properties and multiple connected components,” IEEE Transactions on Signal Processing, vol. 66, no. 9, pp. 2399–2413, 2018.
  14. K.-S. Lu, E. Pavez, and A. Ortega, “On learning laplacians of tree structured graphs,” in 2018 IEEE Data Science Workshop (DSW).   IEEE, 2018, pp. 205–209.
  15. G. Mateos, S. Segarra, A. G. Marques, and A. Ribeiro, “Connecting the dots: Identifying network structure via graph signal processing,” IEEE Signal Processing Magazine, vol. 36, no. 3, pp. 16–43, 2019.
  16. X. Dong, D. Thanou, M. Rabbat, and P. Frossard, “Learning graphs from data: A signal representation perspective,” IEEE Signal Processing Magazine, vol. 36, no. 3, pp. 44–63, 2019.
  17. H. E. Egilmez, Y.-H. Chao, and A. Ortega, “Graph-based transforms for video coding,” IEEE Transactions on Image Processing, vol. 29, pp. 9330–9344, 2020.
  18. E. Pavez, “Laplacian constrained precision matrix estimation: Existence and high dimensional consistency,” in International Conference on Artificial Intelligence and Statistics.   PMLR, 2022, pp. 9711–9722.
  19. A. King, “Online k-means clustering of nonstationary data,” Prediction Project Report, pp. 1–9, 2012.
  20. B. Caputo, E. Hayman, and P. Mallikarjuna, “Class-specific material categorisation,” in Tenth IEEE International Conference on Computer Vision (ICCV’05) Volume 1, vol. 2.   IEEE, 2005, pp. 1597–1604.
  21. S. Lazebnik, C. Schmid, and J. Ponce, “A sparse texture representation using local affine regions,” IEEE transactions on pattern analysis and machine intelligence, vol. 27, no. 8, pp. 1265–1278, 2005.
  22. G. Bjontegaard, “Calculation of average psnr differences between rd-curves,” ITU SG16 Doc. VCEG-M33, 2001.
  23. A. Chu, C. M. Sehgal, and J. F. Greenleaf, “Use of gray value distribution of run lengths for texture analysis,” Pattern recognition letters, vol. 11, no. 6, pp. 415–419, 1990.
Citations (2)

Summary

We haven't generated a summary for this paper yet.