Abstract
In an end-to-end learned image compression framework, an encoder projects the image on a low-dimensional, quantized, latent space while a decoder recovers the original image. The encoder and decoder are jointly trained with standard gradient backpropagation to minimize a rate-distortion (RD) cost function accounting for both distortions between the original and reconstructed image and the quantized latent space rate. State-of-the-art methods rely on an auxiliary neural network to estimate the rate R of the latent space. We propose a non-parametric entropy model that estimates the statistical frequencies of the quantized latent space during training. The proposed model is differentiable, so it can be plugged into the cost function to be minimized as a rate proxy and can be adapted to a given context without retraining. Our experiments show comparable performance with a learned rate estimator and better performance when is adapted over a temporal context.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The code is publicly available on https://github.com/EIDOSLAB/SFC.
References
Ma, S., et al.: Image and video compression with neural networks: a review. In: IEEE TCSVT (2019)
Ballé, J., Laparra, V., Simoncelli, E.P.: End-to-end optimized image compression. In: ICLR, Simoncelli (2017)
Ballé, J., Minnen, D., Singh, S., Hwang, S.J., Johnston, N.: Variational image compression with a scale hyperprior. In: ICLR (2018)
Minnen, D., et al.: Joint autoregressive and hierarchical priors for learned image compression. In: Advances in Neural Information Processing Systems (2018)
Lee, J., et al.: Context-adaptive entropy model for end-to-end optimized image compression. In: International Conference on Learning Representations (ICLR) (2019)
Minnen, D., Saurabh, S.: Channel-wise autoregressive entropy models for learned image compression. In: IEEE International Conference on Image Processing (2020)
Yang, C., et al.: Graph-convolution network for image compression. In: IEEE International Conference on Image Processing (ICIP) (2021)
Cheng, Z., e al.: Learned image compression with discretized gaussian mixture likelihoods and attention modules. In: CVPR (2020)
Zou, R., et al.: The devil is in the details: window-based attention for image compression. In: CVPR (2022)
Goyal, V.K.: Theoretical foundations of transform coding. In: IEEE Signal Processing Magazine (2001)
Robert, M., Neuhoff, D.: Quantization. In: IEEE Transactions on Information Theory (1998)
Lee, J., et al.: DPICT: deep progressive image compression using trit-planes. In: IEEE/CVF CVPR (2022)
Eastman Kodak Company. Kodak Lossless True Color Image Suite (1999)
Toderici, G., et al.: Workshop and challenge on learned image compression. In: CVPR (2021)
Joint Video Exploration Team (JVET) of ITU-T SG16 WP3 andISO/IEC JTC1/SC29/WG11: JVET-G1010: JVET common test conditions and software reference configurations, in 7th Meeting, Torino (IT) (2017)
Xue, T., et al.: Video enhancement with task-oriented flow. In: International Journal of Computer Vision (IJCV) (2019)
Bégaint, J., et al.: CompressAI: a PyTorch library and evaluation platform for end-to-end compression research. In arXiv preprint arXiv:2011.03029 (2020)
Bjontegaard, G.: Calculation of average PSNR differences between RD-curves. In: VCEG-M33 (2001)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Presta, A., Fiandrotti, A., Tartaglione, E., Grangetto, M. (2023). A Differentiable Entropy Model for Learned Image Compression. In: Foresti, G.L., Fusiello, A., Hancock, E. (eds) Image Analysis and Processing – ICIAP 2023. ICIAP 2023. Lecture Notes in Computer Science, vol 14233. Springer, Cham. https://doi.org/10.1007/978-3-031-43148-7_28
Download citation
DOI: https://doi.org/10.1007/978-3-031-43148-7_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43147-0
Online ISBN: 978-3-031-43148-7
eBook Packages: Computer ScienceComputer Science (R0)