2000 character limit reached
Overfitted image coding at reduced complexity (2403.11651v1)
Published 18 Mar 2024 in eess.IV
Abstract: Overfitted image codecs offer compelling compression performance and low decoder complexity, through the overfitting of a lightweight decoder for each image. Such codecs include Cool-chic, which presents image coding performance on par with VVC while requiring around 2000 multiplications per decoded pixel. This paper proposes to decrease Cool-chic encoding and decoding complexity. The encoding complexity is reduced by shortening Cool-chic training, up to the point where no overfitting is performed at all. It is also shown that a tiny neural decoder with 300 multiplications per pixel still outperforms HEVC. A near real-time CPU implementation of this decoder is made available at https://orange-opensource.github.io/Cool-Chic/.
- “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.
- “MLIC++: Linear complexity multi-reference entropy modeling for learned image compression,” in ICML 2023 Workshop Neural Compression: From Information Theory to Applications, 2023.
- Gary J. Sullivan et al., “Overview of the high efficiency video coding (HEVC) standard,” IEEE Transactions on Circuits and Systems for Video Technology, 2012.
- B. Bross et al., “Overview of the versatile video coding (VVC) standard and its applications,” IEEE Transactions on Circuits and Systems for Video Technology, 2021.
- “COOL-CHIC: coordinate-based low complexity hierarchical image codec,” in IEEE/CVF International Conference on Computer Vision, ICCV 2023. 2023, IEEE.
- “Low-complexity overfitted neural image codec,” in 25th IEEE International Workshop on Multimedia Signal Processing, MMSP 2023. 2023, IEEE.
- “C3: high-performance and low-complexity neural compression from a single image or video,” CoRR, 2023.
- “Kodak image dataset,” http://r0k.us/graphics/kodak/.
- “Cool-chic repository,” https://orange-opensource.github.io/Cool-Chic/.
- “Fast implicit neural representation image codec in resource-limited devices,” CoRR, 2024.
- “Hybrid implicit neural image compression with subpixel context model and iterative pruner,” in 2023 IEEE International Conference on Visual Communications and Image Processing (VCIP).
- “Learned image compression with discretized gaussian mixture likelihoods and attention modules,” in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR.
- “Variational image compression with a scale hyperprior,” in International Conference on Learning Representations, 2018.
- CLIC20, “Challenge on learned image coding 2020,” http://clic.compression.cc/2021/tasks/index.html, 2020.
- “Automatic differentiation in machine learning: a survey,” Journal of Marchine Learning Research, vol. 18, pp. 1–43, 2018.
- “A convnet for the 2020s,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 11976–11986.
- “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016.
- “Bag of tricks for image classification with convolutional neural networks,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 558–567.
- CLIC19, “Challenge on learned image compression 2019,” https://clic.compression.cc/2019/challenge/, 2019.
- “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
- “COIN++: data agnostic neural compression,” CoRR, vol. abs/2201.12904, 2022.
- “Computationally-efficient neural image compression with shallow decoders,” in IEEE/CVF International Conference on Computer Vision, ICCV 2023. pp. 530–540, IEEE.