2000 character limit reached
Adapting Learned Image Codecs to Screen Content via Adjustable Transformations (2402.17544v1)
Published 27 Feb 2024 in eess.IV, cs.CV, and cs.LG
Abstract: As learned image codecs (LICs) become more prevalent, their low coding efficiency for out-of-distribution data becomes a bottleneck for some applications. To improve the performance of LICs for screen content (SC) images without breaking backwards compatibility, we propose to introduce parameterized and invertible linear transformations into the coding pipeline without changing the underlying baseline codec's operation flow. We design two neural networks to act as prefilters and postfilters in our setup to increase the coding efficiency and help with the recovery from coding artifacts. Our end-to-end trained solution achieves up to 10% bitrate savings on SC compression compared to the baseline LICs while introducing only 1% extra parameters.
- “Variational image compression with a scale hyperprior,” arXiv preprint arXiv:1802.01436, 2018.
- “Joint autoregressive and hierarchical priors for learned image compression,” Advances in neural information processing systems, vol. 31, 2018.
- “Learned image compression with discretized gaussian mixture likelihoods and attention modules,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 7939–7948.
- “Contextformer: A transformer with spatio-channel attention for context modeling in learned image compression,” in Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XIX. Springer, 2022, pp. 447–463.
- “Efficient contextformer: Spatio-channel window attention for fast context modeling in learned image compression,” arXiv preprint arXiv:2306.14287, 2023.
- “Elic: Efficient learned image compression with unevenly grouped space-channel contextual adaptive coding,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5718–5727.
- “Learned image compression with mixed transformer-cnn architectures,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 14388–14397.
- “An open video dataset for screen content coding,” in 2022 Picture Coding Symposium (PCS). Dec. 2022, IEEE.
- “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.
- “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.
- “Overview of hevc extensions on screen content coding,” APSIPA Transactions on Signal and Information Processing, vol. 4, pp. e10, 2015.
- “Overview of screen content coding in recently developed video coding standards,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 2, pp. 839–852, 2022.
- “End-to-end optimized image compression,” arXiv preprint arXiv:1611.01704, 2016.
- “An end-to-end compression framework based on convolutional neural networks,” in 2017 Data Compression Conference (DCC), 2017, pp. 463–463.
- “Sandwiched image compression: Wrapping neural networks around a standard codec,” in 2021 IEEE International Conference on Image Processing (ICIP), 2021, pp. 3757–3761.
- “Sandwiched image compression: Increasing the resolution and dynamic range of standard codecs,” in 2022 Picture Coding Symposium (PCS), 2022, Best Paper Finalist.
- Roger Penrose, “A generalized inverse for matrices,” Mathematical Proceedings of the Cambridge Philosophical Society, vol. 51, no. 3, pp. 406–413, July 1955.
- Stuart Lloyd, “Least squares quantization in pcm,” IEEE Transactions on Information Theory, vol. 28, no. 2, pp. 129–137, Mar. 1982.
- “Deep residual learning for image recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 2016, IEEE.
- “EfficientNet: Rethinking model scaling for convolutional neural networks,” in Proceedings of the 36th International Conference on Machine Learning, Kamalika Chaudhuri and Ruslan Salakhutdinov, Eds. 09–15 Jun 2019, vol. 97 of Proceedings of Machine Learning Research, pp. 6105–6114, PMLR.
- “Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 1874–1883.
- “The jpeg ai standard: Providing efficient human and machine visual data consumption,” IEEE MultiMedia, vol. 30, no. 1, pp. 100–111, 2023.
- “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
- “Compressai: a pytorch library and evaluation platform for end-to-end compression research,” arXiv preprint arXiv:2011.03029, 2020.
- Gisle Bjøntegaard, “Calculation of average psnr differences between rd-curves,” 2001.
- “Beyond bjøntegaard: Limits of video compression performance comparisons,” in 2022 IEEE International Conference on Image Processing (ICIP). IEEE, 2022, pp. 46–50.