Variable Rate Image Compression with Content Adaptive Optimization

In this paper, we propose a variable rate image compression framework for low bit-rate image compression task. Unlike most of the variational auto-encoder (VAE) based methods, our proposal is able to achieve continuously variable rate in a single model by introducing a pair of gain units into VAE. Besides, a content adaptive optimization is applied to adapt the latent representation to the specific content while keeping the parameters of the network and the predictive model fixed. After that, due to the variable rate characteristics of our method, each image can be compressed into any quality level through a unified codec. Finally, an efficient rate control algorithm is designed to find the optimal bit allocation scheme under the constraint of the low rate challenge.

[1]  Lucas Theis,et al.  Lossy Image Compression with Compressive Autoencoders , 2017, ICLR.

[2]  David Minnen,et al.  Integer Networks for Data Compression with Latent-Variable Models , 2019, ICLR.

[3]  Valero Laparra,et al.  Density Modeling of Images using a Generalized Normalization Transformation , 2015, ICLR.

[4]  Alpár Jüttner,et al.  Lagrange relaxation based method for the QoS routing problem , 2001, Proceedings IEEE INFOCOM 2001. Conference on Computer Communications. Twentieth Annual Joint Conference of the IEEE Computer and Communications Society (Cat. No.01CH37213).

[5]  Yun Fu,et al.  Residual Non-local Attention Networks for Image Restoration , 2019, ICLR.

[6]  Alex Graves,et al.  Conditional Image Generation with PixelCNN Decoders , 2016, NIPS.

[7]  David Minnen,et al.  Joint Autoregressive and Hierarchical Priors for Learned Image Compression , 2018, NeurIPS.

[8]  Lei Zhou,et al.  End-to-end Optimized Image Compression with Attention Mechanism , 2019, CVPR Workshops.

[9]  Elad Eban,et al.  Computationally Efficient Neural Image Compression , 2019, ArXiv.

[10]  David Minnen,et al.  Variational image compression with a scale hyperprior , 2018, ICLR.

[11]  Luca Benini,et al.  Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations , 2017, NIPS.

[12]  Gregory K. Wallace,et al.  The JPEG still picture compression standard , 1991, CACM.

[13]  Jacob Ziv,et al.  On universal quantization , 1985, IEEE Trans. Inf. Theory.

[14]  Valero Laparra,et al.  End-to-end Optimized Image Compression , 2016, ICLR.

[15]  Jungwon Lee,et al.  Variable Rate Deep Image Compression With a Conditional Autoencoder , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[16]  Michael W. Marcellin,et al.  JPEG2000 - image compression fundamentals, standards and practice , 2013, The Kluwer international series in engineering and computer science.

[17]  Jing Wang,et al.  G-VAE: A Continuously Variable Rate Deep Image Compression Framework , 2020, ArXiv.

[18]  Luc Van Gool,et al.  Conditional Probability Models for Deep Image Compression , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[19]  Yao Wang,et al.  End-to-End Learnt Image Compression via Non-Local Attention Optimization and Improved Context Modeling , 2019, IEEE Transactions on Image Processing.

[20]  Abdelaziz Djelouah,et al.  Content Adaptive Optimization for Neural Image Compression , 2019, CVPR Workshops.