Learned Neural Iterative Decoding for Lossy Image Compression Systems

For lossy image compression systems, we develop an algorithm, iterative refinement, to improve the decoder's reconstruction compared to standard decoding techniques. Specifically, we propose a recurrent neural network approach for nonlinear, iterative decoding. Our decoder, which works with any encoder, employs self-connected memory units that make use of causal and non-causal spatial context information to progressively reduce reconstruction error over a fixed number of steps. We experiment with variants of our estimator and find that iterative refinement consistently creates lower distortion images of higher perceptual quality compared to other approaches. Specifically, on the Kodak Lossless True Color Image Suite, we observe as much as a 0.871 decibel (dB) gain over JPEG, a 1.095 dB gain over JPEG 2000, and a 0.971 dB gain over a competitive neural model.

[1]  PAUL J. WERBOS,et al.  Generalization of backpropagation with application to a recurrent gas market model , 1988, Neural Networks.

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

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

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

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

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

[7]  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.

[8]  David Reitter,et al.  Learning Simpler Language Models with the Differential State Framework , 2017, Neural Computation.

[9]  C. Lee Giles,et al.  Learning and Extracting Finite State Automata with Second-Order Recurrent Neural Networks , 1992, Neural Computation.

[10]  Joshua Snoke,et al.  Using Neural Generative Models to Release Synthetic Twitter Corpora with Reduced Stylometric Identifiability of Users. , 2016 .

[11]  Karvel K. Thornber,et al.  Equivalence in knowledge representation: automata, recurrent neural networks, and dynamical fuzzy systems , 1999, Proc. IEEE.

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

[13]  Majid Rabbani,et al.  An overview of the JPEG 2000 still image compression standard , 2002, Signal Process. Image Commun..

[14]  Nir Shavit,et al.  Generative Compression , 2017, 2018 Picture Coding Symposium (PCS).

[15]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[16]  Seishi Takamura,et al.  Lossless image compression with lossy image using adaptive prediction and arithmetic coding , 1994, Proceedings of IEEE Data Compression Conference (DCC'94).

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

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

[19]  Andrea Giachetti,et al.  TESTIMAGES: A Large Data Archive For Display and Algorithm Testing , 2013, J. Graph. Tools.

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

[21]  Bolei Zhou,et al.  Places: A 10 Million Image Database for Scene Recognition , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[23]  Zhou Wang,et al.  Group MAD Competition? A New Methodology to Compare Objective Image Quality Models , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  L. Alparone,et al.  Context modeling for near-lossless image coding , 2002, IEEE Signal Processing Letters.

[25]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[26]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[27]  Feng Jiang,et al.  An End-to-End Compression Framework Based on Convolutional Neural Networks , 2018, IEEE Transactions on Circuits and Systems for Video Technology.

[28]  Yoshua Bengio,et al.  High quality document image compression with "DjVu" , 1998, J. Electronic Imaging.

[29]  Michael W. Spratling.  A review of predictive coding algorithms , 2017, Brain and Cognition.

[30]  Alvin,et al.  Wallace the JPEG still picture compression standard ' , 2017 .

[31]  Hongyang Chao,et al.  Building Dual-Domain Representations for Compression Artifacts Reduction , 2016, ECCV.

[32]  Gregory K. Wallace,et al.  The JPEG still picture compression standard , 1992 .

[33]  Daan Wierstra,et al.  Towards Conceptual Compression , 2016, NIPS.

[34]  Luca Benini,et al.  Soft-to-Hard Vector Quantization for End-to-End Learned Compression of Images and Neural Networks , 2017, ArXiv.

[35]  Tomaso A. Poggio,et al.  Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex , 2016, ArXiv.

[36]  Giulia Boato,et al.  RAISE: a raw images dataset for digital image forensics , 2015, MMSys.

[37]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[38]  Patrick Mitran,et al.  Turbo source coding: a noise-robust approach to data compression , 2002, Proceedings DCC 2002. Data Compression Conference.

[39]  Richard S. Zemel,et al.  Generative Moment Matching Networks , 2015, ICML.

[40]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.