Abstract
COIN++ is a special variant of Implicit Neural Representation (INR), which encodes signals as modulations applied to the base INR network. It is becoming a promising method for applications in image compression. However, INR’s effectiveness is hindered by its inability to capture high-frequency details in the image representation. We propose a novel COIN++ framework using Chebyshev approximation to enhance high-frequency signal learning and image compression. In addition, we design an adaptable image partitioning technology and an integrated quantization method to further the image compression performance of COIN++ in the framework. Experiments demonstrate our framework significantly enhances both representational capacity and compression rate compared to the COIN++ baseline, with notable PSNR improvements.
Supported by the Natural Science Foundation of Fujian Province of China (No. 2021J01002) and Key Program of the National Natural Science Foundation of China Joint Fund (No. U23A20383).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bai, Y., Yang, X., Liu, X., Jiang, J., Wang, Y., Ji, X., Gao, W.: Towards end-to-end image compression and analysis with transformers. AAAI 36(1), 104–112 (Jun 2022). https://doi.org/10.1609/aaai.v36i1.19884. https://ojs.aaai.org/index.php/AAAI/article/view/19884
Ballé, J., Laparra, V., Simoncelli, E.P.: End-to-end optimized image compression. In: ICLR (2017)
Ballé, J., Minnen, D., Singh, S., Hwang, S.J., Johnston, N.: Variational image compression with a scale hyperprior. In: ICLR (2018)
Bellard, F.: BPG image format (2015). https://bellard.org/bpg/
Benbarka, N., Höfer, T., Zell, A., et al.: Seeing implicit neural representations as Fourier series. In: WCACV, pp. 2041–2050 (2022)
Burden, R.L., Faires, J.D., Burden, A.M.: Numerical Analysis. Cengage Learning, 9th edn. (2015)
Chen, F., Xu, Y., Wang, L.: Two-stage octave residual network for end-to-end image compression. In: AAAI, pp. 3922–3929 (2022)
Chen, Y., Wang, X.: Transformers as meta-learners for implicit neural representations. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol. 13677. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19790-1_11
Chmiel, B., Banner, R., Shomron, G., Nahshan, Y., Bronstein, A., Weiser, U., et al.: Robust quantization: one model to rule them all. NeurIPS 33, 5308–5317 (2020)
Dupont, E., Golinski, A., Alizadeh, M., Teh, Y.W., Doucet, A.: COIN: compression with implicit neural representations (2021). CoRR arXiv:abs/2103.03123
Dupont, E., Loya, H., Alizadeh, M., Golinski, A., Teh, Y.W., Doucet, A.: COIN++: neural compression across modalities. Trans. Mach. Learn. Res. (2022)
Franzen, R.: Kodak lossless true color image suite. http://r0k.us/graphics/kodak/ (1999)
Hong, C., Kim, H., Baik, S., Oh, J., Lee, K.M.: Daq: channel-wise distribution-aware quantization for deep image super-resolution networks. In: WCACV, pp. 2675–2684 (2022)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359–366 (1989)
ITU-T, ISO/IEC: Advanced video coding (avc) standard (h.264). ITU-T Recommendation H.264 and ISO/IEC 14496-10 (2003)
ITU-T, ISO/IEC: High efficiency video coding (hevc) standard (h.265). ITU-T Recommendation H.265 and ISO/IEC 23008-2 (2013)
ITU-T, ISO/IEC: Versatile video coding (vvc) standard (h.266). ITU-T Recommendation H.266 and ISO/IEC 23090-3 (2020)
Jiang, X., Tan, W., Tan, T., Yan, B., Shen, L.: Multi-modality deep network for extreme learned image compression. In: AAAI, pp. 1033–1041 (2023)
Kim, C., Lee, D., Kim, S., Cho, M., Han, W.S.: Generalizable implicit neural representations via instance pattern composers. In: CVPR, pp. 11808–11817 (2023)
Lee, J., Tack, J., Lee, N., Shin, J.: Meta-learning sparse implicit neural representations. NeurIPS 34, 11769–11780 (2021)
Li, Y., Dong, X., Wang, W.: Additive powers-of-two quantization: an efficient non-uniform discretization for neural networks (2019). arXiv:1909.13144
Martel, J.N., Lindell, D.B., Lin, C.Z., Chan, E.R., Monteiro, M., Wetzstein, G.: Acorn: adaptive coordinate networks for neural scene representation. ACM TOG 40(4), 1–13 (2021)
Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science, vol. 12346. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_24
Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis (2020). arXiv:2003.08934v2
Ramasinghe, S., Lucey, S.: Beyond periodicity: towards a unifying framework for activations in coordinate-MLPs. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol. 13693. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-19827-4_9
Saragadam, V., Tan, J., Balakrishnan, G., Baraniuk, R.G., Veeraraghavan, A.: MINER: multiscale implicit neural representation. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol. 13683. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-20050-2_19
Schwarz, J., Teh, Y.W.: Meta-learning sparse compression networks. J. Mach. Learn. Res. (2022)
Sitzmann, V., Martel, J., Bergman, A., Lindell, D., Wetzstein, G.: Implicit neural representations with periodic activation functions. NeurIPS 33, 7462–7473 (2020)
Stanley, K.O.: Compositional pattern producing networks: a novel abstraction of development. Genet. Program Evolvable Mach. 8, 131–162 (2007)
Strümpler, Y., Postels, J., Yang, R., Gool, L.V., Tombari, F.: Implicit neural representations for image compression. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds.) ECCV, pp. 74–91. Springer Nature Switzerland, Cham (2022)
Tancik, M., Srinivasan, P., Mildenhall, B., Fridovich-Keil, S., Raghavan, N., Singhal, U., Ramamoorthi, R., Barron, J., Ng, R.: Fourier features let networks learn high frequency functions in low dimensional domains. NeurIPS 33, 7537–7547 (2020)
Taubman, D.S., Marcellin, M.W., Rabbani, M.: Jpeg 2000: image compression fundamentals, standards and practice. J. Electron. Imaging 11(2), 286–287 (2002)
Trefethen, L.N.: Approximation Theory and Approximation Practice, Extended Edition. SIAM (2019)
Wallace, G.K.: The jpeg still picture compression standard. IEEE Trans. Consum. Electron. 38(1), xviii–xxxiv (1992)
Yamamoto, K.: Learnable companding quantization for accurate low-bit neural networks. In: CVPR, pp. 5029–5038 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chu, H. et al. (2025). CPE COIN++: Towards Optimized Implicit Neural Representation Compression Via Chebyshev Positional Encoding. In: Lin, Z., et al. Pattern Recognition and Computer Vision. PRCV 2024. Lecture Notes in Computer Science, vol 15039. Springer, Singapore. https://doi.org/10.1007/978-981-97-8692-3_36
Download citation
DOI: https://doi.org/10.1007/978-981-97-8692-3_36
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-8691-6
Online ISBN: 978-981-97-8692-3
eBook Packages: Computer ScienceComputer Science (R0)