How to Exploit the Transferability of Learned Image Compression to Conventional Codecs

Lossy image compression is often limited by the simplicity of the chosen loss measure. Recent research suggests that generative adversarial networks have the ability to overcome this limitation and serve as a multi-modal loss, especially for textures. Together with learned image compression, these two techniques can be used to great effect when relaxing the commonly employed tight measures of distortion. However, convolutional neural network-based algorithms have a large computational footprint. Ideally, an existing conventional codec should stay in place, ensuring faster adoption and adherence to a balanced computational envelope.As a possible avenue to this goal, we propose and investigate how learned image coding can be used as a surrogate to optimise an image for encoding. A learned filter alters the image to optimise a different performance measure or a particular task. Extending this idea with a generative adversarial network, we show how entire textures are replaced by ones that are less costly to encode but preserve a sense of detail.Our approach can remodel a conventional codec to adjust for the MS-SSIM distortion with over 20% rate improvement without any decoding overhead. On task-aware image compression, we perform favourably against a similar but codec-specific approach.

[1]  Sepp Hochreiter,et al.  Learning to Learn Using Gradient Descent , 2001, ICANN.

[2]  Akshay Pushparaja,et al.  CompressAI: a PyTorch library and evaluation platform for end-to-end compression research , 2020, ArXiv.

[3]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[4]  Michael Elad,et al.  Better Compression With Deep Pre-Editing , 2020, IEEE Transactions on Image Processing.

[5]  Radu Timofte,et al.  Learning to Improve Image Compression without Changing the Standard Decoder , 2020, ECCV Workshops.

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

[7]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[9]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Luc Van Gool,et al.  Generative Adversarial Networks for Extreme Learned Image Compression , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[11]  Marcin Andrychowicz,et al.  Learning to learn by gradient descent by gradient descent , 2016, NIPS.

[12]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[13]  David Minnen,et al.  Variable Rate Image Compression with Recurrent Neural Networks , 2015, ICLR.

[14]  Vladlen Koltun,et al.  Learning to Inpaint for Image Compression , 2017, NIPS.

[15]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

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

[17]  Raymond Y. K. Lau,et al.  Least Squares Generative Adversarial Networks , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[19]  David Minnen,et al.  Full Resolution Image Compression with Recurrent Neural Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Qionghai Dai,et al.  Residual Highway Convolutional Neural Networks for in-loop Filtering in HEVC , 2018, IEEE Transactions on Image Processing.

[21]  Tong Chen,et al.  Gated Context Model with Embedded Priors for Deep Image Compression , 2019, 1902.10480.

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

[23]  Steve Branson,et al.  Learned Video Compression , 2018, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[24]  Xinfeng Zhang,et al.  Content-Aware Convolutional Neural Network for In-Loop Filtering in High Efficiency Video Coding , 2019, IEEE Transactions on Image Processing.

[25]  Eirikur Agustsson,et al.  High-Fidelity Generative Image Compression , 2020, NeurIPS.

[26]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[27]  Ajay Luthra,et al.  Overview of the H.264/AVC video coding standard , 2003, IEEE Trans. Circuits Syst. Video Technol..

[28]  Xiaoyun Zhang,et al.  DVC: An End-To-End Deep Video Compression Framework , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[30]  Misha Denil,et al.  Learning to Learn without Gradient Descent by Gradient Descent , 2016, ICML.

[31]  David Minnen,et al.  Improved Lossy Image Compression with Priming and Spatially Adaptive Bit Rates for Recurrent Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[32]  Lubomir D. Bourdev,et al.  Real-Time Adaptive Image Compression , 2017, ICML.

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

[34]  Liang-Gee Chen,et al.  Decoded GoP 0 : Residual Training GoP 0 : Parameters Quantisation Test on GoP 0 Compression GoP 1 : Decoded Test on GoP 1 GoP 1 : Residual Training GoP , 2019 .

[35]  Gary J. Sullivan,et al.  Overview of the High Efficiency Video Coding (HEVC) Standard , 2012, IEEE Transactions on Circuits and Systems for Video Technology.

[36]  Bohyung Han,et al.  Task-Aware Quantization Network for JPEG Image Compression , 2020, ECCV.

[37]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  David Zhang,et al.  Learning Convolutional Networks for Content-Weighted Image Compression , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[39]  Liang-Gee Chen,et al.  Learning a Code-Space Predictor by Exploiting Intra-Image-Dependencies , 2018, BMVC.

[40]  Jan Kautz,et al.  High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.