Learning Scalable ℓ∞-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression

We propose a novel joint lossy image and residual compression framework for learning $\ell_\infty$-constrained near-lossless image compression. Specifically, we obtain a lossy reconstruction of the raw image through lossy image compression and uniformly quantize the corresponding residual to satisfy a given tight $\ell_\infty$ error bound. Suppose that the error bound is zero, i.e., lossless image compression, we formulate the joint optimization problem of compressing both the lossy image and the original residual in terms of variational auto-encoders and solve it with end-to-end training. To achieve scalable compression with the error bound larger than zero, we derive the probability model of the quantized residual by quantizing the learned probability model of the original residual, instead of training multiple networks. We further correct the bias of the derived probability model caused by the context mismatch between training and inference. Finally, the quantized residual is encoded according to the bias-corrected probability model and is concatenated with the bitstream of the compressed lossy image. Experimental results demonstrate that our near-lossless codec achieves the state-of-the-art performance for lossless and near-lossless image compression, and achieves competitive PSNR while much smaller $\ell_\infty$ error compared with lossy image codecs at high bit rates.

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

[2]  Jiro Katto,et al.  Learned Image Compression With Discretized Gaussian Mixture Likelihoods and Attention Modules , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[4]  Ian H. Witten,et al.  Arithmetic coding for data compression , 1987, CACM.

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

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

[7]  Vivek K. Goyal,et al.  Theoretical foundations of transform coding , 2001, IEEE Signal Process. Mag..

[8]  Tenkasi V. Ramabadran,et al.  Near-lossless compression of medical images through entropy-coded DPCM , 1994, IEEE Trans. Medical Imaging.

[9]  Emiel Hoogeboom,et al.  Integer Discrete Flows and Lossless Compression , 2019, NeurIPS.

[10]  Pieter Abbeel,et al.  Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables , 2019, ICML.

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

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

[13]  Luc Van Gool,et al.  Learning Better Lossless Compression Using Lossy Compression , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[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]  Eirikur Agustsson,et al.  NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

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

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

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

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

[21]  Touradj Ebrahimi,et al.  The JPEG 2000 still image compression standard , 2001, IEEE Signal Process. Mag..

[22]  Houqiang Li,et al.  End-to-End Optimized Versatile Image Compression With Wavelet-Like Transform , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[24]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[25]  Jooyoung Lee,et al.  Context-adaptive Entropy Model for End-to-end Optimized Image Compression , 2018, ICLR.

[26]  Michael W. Marcellin,et al.  Near-lossless image compression: minimum-entropy, constrained-error DPCM , 1995, Proceedings., International Conference on Image Processing.

[27]  Thomas M. Cover,et al.  Elements of Information Theory (Wiley Series in Telecommunications and Signal Processing) , 2006 .

[28]  David Zhang,et al.  Learning Content-Weighted Deep Image Compression , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[30]  Xi Zhang,et al.  Ultra High Fidelity Deep Image Decompression With l∞-Constrained Compression , 2020, IEEE Transactions on Image Processing.

[31]  David Barber,et al.  Practical Lossless Compression with Latent Variables using Bits Back Coding , 2019, ICLR.

[32]  Nasir D. Memon,et al.  Context-based, adaptive, lossless image coding , 1997, IEEE Trans. Commun..

[33]  Zhizheng Zhang,et al.  3-D Context Entropy Model for Improved Practical Image Compression , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[34]  Diederik P. Kingma,et al.  An Introduction to Variational Autoencoders , 2019, Found. Trends Mach. Learn..

[35]  Xi Chen,et al.  PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications , 2017, ICLR.

[36]  Paul W. Melnychuck,et al.  Survey Of Lossless Image Coding Techniques , 1989, Photonics West - Lasers and Applications in Science and Engineering.

[37]  Guillermo Sapiro,et al.  The LOCO-I lossless image compression algorithm: principles and standardization into JPEG-LS , 2000, IEEE Trans. Image Process..

[38]  Zhou Wang,et al.  Multiscale structural similarity for image quality assessment , 2003, The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003.

[39]  Koray Kavukcuoglu,et al.  Pixel Recurrent Neural Networks , 2016, ICML.

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

[41]  Xiaolin Wu,et al.  Near-Lossless ℓ∞-Constrained Image Decompression via Deep Neural Network , 2019, 2019 Data Compression Conference (DCC).

[42]  Luc Van Gool,et al.  Practical Full Resolution Learned Lossless Image Compression , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[44]  Jon Sneyers,et al.  FLIF: Free lossless image format based on MANIAC compression , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[45]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .