Ultra High Fidelity Deep Image Decompression With l∞-Constrained Compression

We propose a novel asymmetric image compression system of light <inline-formula> <tex-math notation="LaTeX">$\ell _\infty $ </tex-math></inline-formula>-constrained predictive encoding and heavy-duty CNN-based soft decoding. The system achieves superior rate-distortion performances over the best of existing image compression methods, including BPG, WebP, FLIF and recent CNN codecs, in both <inline-formula> <tex-math notation="LaTeX">$\ell _{2}$ </tex-math></inline-formula> and <inline-formula> <tex-math notation="LaTeX">$\ell _\infty $ </tex-math></inline-formula> error metrics, for bit rates near or above the threshold of perceptually transparent reconstruction. These remarkable coding gains are made by deep learning for compression artifact removal. A restoration CNN is designed to map a lossy compressed image to its original. Its unique strength is to enforce a tight error bound on a per pixel basis. As such, no small distinctive structures of the original image can be dropped or distorted, even if they are statistical outliers that are otherwise sacrificed by mainstream CNN restoration methods.

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

[2]  Jae Lim,et al.  Reduction Of Blocking Effects In Image Coding , 1984 .

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

[4]  Weisi Lin,et al.  Efficient Image Deblocking Based on Postfiltering in Shifted Windows , 2008, IEEE Transactions on Circuits and Systems for Video Technology.

[5]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[6]  Yun Fu,et al.  Residual Dense Network for Image Restoration , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Yun Fu,et al.  Image Super-Resolution Using Very Deep Residual Channel Attention Networks , 2018, ECCV.

[8]  Nasir D. Memon,et al.  CALIC-a context based adaptive lossless image codec , 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

[9]  Wen Gao,et al.  Compression Artifact Reduction by Overlapped-Block Transform Coefficient Estimation With Block Similarity , 2013, IEEE Transactions on Image Processing.

[10]  Lei Zhang,et al.  l2 Restoration of l∞-Decoded Images Via Soft-Decision Estimation , 2012, IEEE Trans. Image Process..

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

[12]  Michael G. Strintzis,et al.  Lossless image compression based on optimal prediction, adaptive lifting, and conditional arithmetic coding , 2001, IEEE Trans. Image Process..

[13]  A. Robert Calderbank,et al.  Lossless image compression using integer to integer wavelet transforms , 1997, Proceedings of International Conference on Image Processing.

[14]  Narendra Ahuja,et al.  Single image super-resolution from transformed self-exemplars , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[16]  Xiaolin Wu,et al.  Linfinity constrained high-fidelity image compression via adaptive context modeling , 2000, IEEE Trans. Image Process..

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

[18]  Xi Zhang,et al.  Nonlinear Prediction of Multidimensional Signals via Deep Regression with Applications to Image Coding , 2018, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[19]  Wuzhen Shi,et al.  Single image super-resolution with dilated convolution based multi-scale information learning inception module , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[20]  Xiaolin Wu,et al.  L2 Optimized Predictive Image Coding with L∞ Bound , 2013, ICASSP 2013.

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

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

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

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

[25]  Jiantao Zhou,et al.  Sparsity-driven reconstruction of ℓ∞-decoded images , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

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

[27]  Kristian Bredies,et al.  A Total Variation-Based JPEG Decompression Model , 2012, SIAM J. Imaging Sci..

[28]  Xianming Liu,et al.  Data-Driven Soft Decoding of Compressed Images in Dual Transform-Pixel Domain , 2016, IEEE Transactions on Image Processing.

[29]  Shao-Ping Lu,et al.  Wavelet-Based L ∞ Semi-regular Mesh Coding. , 2017 .

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

[31]  Mingxuan Sun,et al.  Dilated Deep Residual Network for Image Denoising , 2017, 2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI).

[32]  Hongyang Chao,et al.  One-To-Many Network for Visually Pleasing Compression Artifacts Reduction , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Lei Zhang,et al.  Convolutional Neural Networks for Image Denoising and Restoration , 2018 .

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

[35]  Joan L. Mitchell,et al.  JPEG: Still Image Data Compression Standard , 1992 .

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

[37]  Yu-Bin Yang,et al.  Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections , 2016, ArXiv.

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

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

[40]  Pavel Zemcík,et al.  Compression Artifacts Removal Using Convolutional Neural Networks , 2016, J. WSCG.

[41]  Michael S. Brown,et al.  A Contrast Enhancement Framework with JPEG Artifacts Suppression , 2014, ECCV.

[42]  Kyoung Mu Lee,et al.  Enhanced Deep Residual Networks for Single Image Super-Resolution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[43]  Michael K. Ng,et al.  Reducing Artifacts in JPEG Decompression Via a Learned Dictionary , 2014, IEEE Transactions on Signal Processing.

[44]  N. Memon,et al.  A progressive Lossless/Near-Lossless image compression algorithm , 2002, IEEE Signal Processing Letters.

[45]  Sorina Dumitrescu,et al.  ℓ2 Optimized Predictive Image Coding With ℓ∞ Bound , 2013, IEEE Trans. Image Process..

[46]  Xi Zhang,et al.  DAVD-Net: Deep Audio-Aided Video Decompression of Talking Heads , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

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

[48]  Alberto Del Bimbo,et al.  Deep Generative Adversarial Compression Artifact Removal , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

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

[50]  Alan C. Bovik,et al.  A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms , 2006, IEEE Transactions on Image Processing.

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

[52]  Gregory Shakhnarovich,et al.  Deep Back-Projection Networks for Super-Resolution , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

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

[54]  Xiaolin Wu,et al.  L2 restoration of L∞-decoded images with context modeling , 2011, 2011 18th IEEE International Conference on Image Processing.

[55]  Xiaoou Tang,et al.  Compression Artifacts Reduction by a Deep Convolutional Network , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

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

[57]  Jacques Froment,et al.  Adapted Total Variation for Artifact Free Decompression of JPEG Images , 2005, Journal of Mathematical Imaging and Vision.

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