Unraveling Neural Cellular Automata for Lightweight Image Compression
Resumo
Neural Cellular Automata (NCA) are computational models inspired by cellular growth, capable of learning complex behaviours through local interactions. While NCAs have been applied to various tasks like image restoration and synthesis, their potential for image compression remains largely unexplored. This paper aims to unravel the capabilities of NCAs for lightweight image compression by introducing a Grid Neural Cellular Automata (GNCA) training strategy. Unlike traditional methods that depend on large deep learning models, NCAs offer a low-cost, compact and highly parallelizable alternative with intrinsic robustness to noise. Through experiments on the COCO 2017 dataset, we compare the compression performance of NCAs against JPEG, JPEG-2000 and WebP, using the metrics PSNR, SSIM, MSE and Compression Rate. Our results demonstrate that NCAs achieve competitive compression rates and image quality reconstruction, highlighting their potential as a lightweight solution for efficient image compression.
Referências
A. G. Hoekstra, J. Kroc, and P. M. Sloot, Simulating complex systems by cellular automata. Springer, 2010.
A. Mordvintsev, E. Randazzo, E. Niklasson, and M. Levin, “Growing neural cellular automata,” Distill, vol. 5, no. 2, p. e23, 2020.
S. Sudhakaran, D. Grbic, S. Li, A. Katona, E. Najarro, C. Glanois, and S. Risi, “Growing 3d artefacts and functional machines with neural cellular automata,” in Artificial Life Conference Proceedings 33, vol. 2021, no. 1. MIT Press One Rogers Street, Cambridge, MA 02142-1209, USA journals-info . . . , 2021, p. 108.
A. Variengien, S. Nichele, T. Glover, and S. Pontes-Filho, “Towards self-organized control: Using neural cellular automata to robustly control a cart-pole agent,” arXiv preprint arXiv:2106.15240, 2021.
X. Zhu, J. Song, L. Gao, F. Zheng, and H. T. Shen, “Unified multivariate gaussian mixture for efficient neural image compression,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 17 612–17 621.
X. Liu, L. Zhang, Z. Guo, T. Han, M. Ju, B. Xu, H. Liu et al., “Medical image compression based on variational autoencoder,” Mathematical Problems in Engineering, vol. 2022, 2022.
G. K. Wallace, “The jpeg still picture compression standard,” Communications of the ACM, vol. 34, no. 4, pp. 30–44, 1991.
M. W. Marcellin, M. J. Gormish, A. Bilgin, and M. P. Boliek, “An overview of jpeg-2000,” in Proceedings DCC 2000. Data compression conference. IEEE, 2000, pp. 523–541.
Z. Si and K. Shen, “Research on the webp image format,” in Advanced graphic communications, packaging technology and materials. Springer, 2016, pp. 271–277.
S. Shirani, “Data compression: The complete reference (by d. salomon; 2007)[book review],” IEEE Signal Processing Magazine, vol. 25, no. 2, pp. 147–149, 2008.
K. Ding, K. Ma, S. Wang, and E. P. Simoncelli, “Image quality assessment: Unifying structure and texture similarity,” IEEE transactions on pattern analysis and machine intelligence, vol. 44, no. 5, pp. 2567–2581, 2020.
J. R. Thompson, “Some shrinkage techniques for estimating the mean,” Journal of the American Statistical Association, vol. 63, no. 321, pp. 113–122, 1968.
T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, “Microsoft coco: Common objects in context,” arXiv preprint arXiv:1405.0312, 2014.
M. Sandler, A. Zhmoginov, L. Luo, A. Mordvintsev, E. Randazzo et al., “Image segmentation via cellular automata,” arXiv preprint arXiv:2008.04965, 2020.
E. Najarro, S. Sudhakaran, C. Glanois, and S. Risi, “Hypernca: Growing developmental networks with neural cellular automata,” arXiv preprint arXiv:2204.11674, 2022.
R. B. Palm, M. González-Duque, S. Sudhakaran, and S. Risi, “Variational neural cellular automata,” in 10th International Conference on Learning Representations, ICLR 2022, 2022.
A. Menta, A. Archetti, and M. Matteucci, “Latent neural cellular automata for resource-efficient image restoration,” arXiv preprint arXiv:2403.15525, 2024.
K. Paul, D. R. Choudhury, and P. P. Chaudhuri, “Cellular automata based transform coding for image compression,” in High Performance Computing–HiPC’99: 6th International Conference, Calcutta, India, December 17-20, 1999. Proceedings 6. Springer, 1999, pp. 269–273.
D. Mishra, S. K. Singh, and R. K. Singh, “Deep architectures for image compression: a critical review,” Signal Processing, vol. 191, p. 108346, 2022.
Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, “A survey of convolutional neural networks: analysis, applications, and prospects,” IEEE transactions on neural networks and learning systems, vol. 33, no. 12, pp. 6999–7019, 2021.
L. Medsker and L. C. Jain, Recurrent neural networks: design and applications. CRC press, 1999.
J. Gui, Z. Sun, Y. Wen, D. Tao, and J. Ye, “A review on generative adversarial networks: Algorithms, theory, and applications,” IEEE transactions on knowledge and data engineering, vol. 35, no. 4, pp. 3313–3332, 2021.
H. T. Sadeeq, T. H. Hameed, A. S. Abdi, and A. N. Abdulfatah, “Image compression using neural networks: a review,” International Journal of Online and Biomedical Engineering (iJOE), vol. 17, no. 14, pp. 135–153, 2021.
W. Jiang and R. Wang, “Mlic++: Linear complexity multi-reference entropy modeling for learned image compression,” in ICML 2023 Workshop Neural Compression: From Information Theory to Applications, 2023. [Online]. Available: [link]
A. Hernandez, A. Vilalta, and F. Moreno-Noguer, “Neural cellular automata manifold,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 10 020–10 028.
L. B. Almeida, “Multilayer perceptrons,” in Handbook of Neural Computation. CRC Press, 2020, pp. C1–2.
A. Mordvintsev and E. Niklasson, “µnca: Texture generation with ultracompact neural cellular automata,” arXiv preprint arXiv:2111.13545, 2021.
M. Friedman, “The use of ranks to avoid the assumption of normality implicit in the analysis of variance,” Journal of the american statistical association, vol. 32, no. 200, pp. 675–701, 1937.
D. J. Sheskin, Handbook of parametric and nonparametric statistical procedures. Chapman and hall/CRC, 2003.
A. Mordvintsev, E. Randazzo, E. Niklasson, and M. Levin, “Growing neural cellular automata,” Distill, vol. 5, no. 2, p. e23, 2020.
S. Sudhakaran, D. Grbic, S. Li, A. Katona, E. Najarro, C. Glanois, and S. Risi, “Growing 3d artefacts and functional machines with neural cellular automata,” in Artificial Life Conference Proceedings 33, vol. 2021, no. 1. MIT Press One Rogers Street, Cambridge, MA 02142-1209, USA journals-info . . . , 2021, p. 108.
A. Variengien, S. Nichele, T. Glover, and S. Pontes-Filho, “Towards self-organized control: Using neural cellular automata to robustly control a cart-pole agent,” arXiv preprint arXiv:2106.15240, 2021.
X. Zhu, J. Song, L. Gao, F. Zheng, and H. T. Shen, “Unified multivariate gaussian mixture for efficient neural image compression,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 17 612–17 621.
X. Liu, L. Zhang, Z. Guo, T. Han, M. Ju, B. Xu, H. Liu et al., “Medical image compression based on variational autoencoder,” Mathematical Problems in Engineering, vol. 2022, 2022.
G. K. Wallace, “The jpeg still picture compression standard,” Communications of the ACM, vol. 34, no. 4, pp. 30–44, 1991.
M. W. Marcellin, M. J. Gormish, A. Bilgin, and M. P. Boliek, “An overview of jpeg-2000,” in Proceedings DCC 2000. Data compression conference. IEEE, 2000, pp. 523–541.
Z. Si and K. Shen, “Research on the webp image format,” in Advanced graphic communications, packaging technology and materials. Springer, 2016, pp. 271–277.
S. Shirani, “Data compression: The complete reference (by d. salomon; 2007)[book review],” IEEE Signal Processing Magazine, vol. 25, no. 2, pp. 147–149, 2008.
K. Ding, K. Ma, S. Wang, and E. P. Simoncelli, “Image quality assessment: Unifying structure and texture similarity,” IEEE transactions on pattern analysis and machine intelligence, vol. 44, no. 5, pp. 2567–2581, 2020.
J. R. Thompson, “Some shrinkage techniques for estimating the mean,” Journal of the American Statistical Association, vol. 63, no. 321, pp. 113–122, 1968.
T.-Y. Lin, M. Maire, S. Belongie, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick, “Microsoft coco: Common objects in context,” arXiv preprint arXiv:1405.0312, 2014.
M. Sandler, A. Zhmoginov, L. Luo, A. Mordvintsev, E. Randazzo et al., “Image segmentation via cellular automata,” arXiv preprint arXiv:2008.04965, 2020.
E. Najarro, S. Sudhakaran, C. Glanois, and S. Risi, “Hypernca: Growing developmental networks with neural cellular automata,” arXiv preprint arXiv:2204.11674, 2022.
R. B. Palm, M. González-Duque, S. Sudhakaran, and S. Risi, “Variational neural cellular automata,” in 10th International Conference on Learning Representations, ICLR 2022, 2022.
A. Menta, A. Archetti, and M. Matteucci, “Latent neural cellular automata for resource-efficient image restoration,” arXiv preprint arXiv:2403.15525, 2024.
K. Paul, D. R. Choudhury, and P. P. Chaudhuri, “Cellular automata based transform coding for image compression,” in High Performance Computing–HiPC’99: 6th International Conference, Calcutta, India, December 17-20, 1999. Proceedings 6. Springer, 1999, pp. 269–273.
D. Mishra, S. K. Singh, and R. K. Singh, “Deep architectures for image compression: a critical review,” Signal Processing, vol. 191, p. 108346, 2022.
Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, “A survey of convolutional neural networks: analysis, applications, and prospects,” IEEE transactions on neural networks and learning systems, vol. 33, no. 12, pp. 6999–7019, 2021.
L. Medsker and L. C. Jain, Recurrent neural networks: design and applications. CRC press, 1999.
J. Gui, Z. Sun, Y. Wen, D. Tao, and J. Ye, “A review on generative adversarial networks: Algorithms, theory, and applications,” IEEE transactions on knowledge and data engineering, vol. 35, no. 4, pp. 3313–3332, 2021.
H. T. Sadeeq, T. H. Hameed, A. S. Abdi, and A. N. Abdulfatah, “Image compression using neural networks: a review,” International Journal of Online and Biomedical Engineering (iJOE), vol. 17, no. 14, pp. 135–153, 2021.
W. Jiang and R. Wang, “Mlic++: Linear complexity multi-reference entropy modeling for learned image compression,” in ICML 2023 Workshop Neural Compression: From Information Theory to Applications, 2023. [Online]. Available: [link]
A. Hernandez, A. Vilalta, and F. Moreno-Noguer, “Neural cellular automata manifold,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 10 020–10 028.
L. B. Almeida, “Multilayer perceptrons,” in Handbook of Neural Computation. CRC Press, 2020, pp. C1–2.
A. Mordvintsev and E. Niklasson, “µnca: Texture generation with ultracompact neural cellular automata,” arXiv preprint arXiv:2111.13545, 2021.
M. Friedman, “The use of ranks to avoid the assumption of normality implicit in the analysis of variance,” Journal of the american statistical association, vol. 32, no. 200, pp. 675–701, 1937.
D. J. Sheskin, Handbook of parametric and nonparametric statistical procedures. Chapman and hall/CRC, 2003.
Publicado
30/09/2025
Como Citar
FALCAO, Andreza M. C.; SANTOS, Iury A. X.; CORDEIRO, Filipe R..
Unraveling Neural Cellular Automata for Lightweight Image Compression. In: WORKSHOP DE TRABALHOS EM ANDAMENTO - CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 38. , 2025, Salvador/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 55-60.
