CompressNet: Generative Compression at Extremely Low Bitrates

Compressing images at extremely low bitrates (< 0.1 bpp) has always been a challenging task as the quality of reconstruction significantly reduces due to the strongly imposing constraint on the number of bits allocated for the compressed data. With the increasing need to transfer large amounts of images with limited bandwidth, compressing images to very low sizes is a crucial task. However, the existing methods are not effective at extremely low bitrates. To address this need we propose a novel network called CompressNet which augments a Stacked Autoencoder with a Switch Prediction Network (SAE-SPN). This helps in the reconstruction of visually pleasing images at these low bi-trates (< 0.1 bpp). We benchmark the performance of our proposed method on the Cityscapes dataset, evaluating over different metrics at very low bitrates showing that our method outperforms the other state-of-the-art. In particular, at a bitrate of 0.07, CompressNet achieves 22% lower Perceptual Loss and 55% lower Frechet Inception Distance (FID) compared to the deep learning SOTA methods.

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

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

[3]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

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

[5]  C. Sims.  Rate–distortion theory and human perception , 2016, Cognition.

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

[7]  Hsueh-Ming Hang,et al.  An Autoencoder-based Learned Image Compressor: Description of Challenge Proposal by NCTU , 2018, CVPR Workshops.

[8]  Yochai Blau,et al.  Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff , 2019, ICML.

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

[10]  Tim Fingscheidt,et al.  On Low-Bitrate Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation , 2019, 2019 IEEE Intelligent Vehicles Symposium (IV).

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

[12]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Paul S. Heckbert,et al.  Graphics gems IV , 1994 .

[14]  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.

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

[16]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

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

[18]  Christian Ledig,et al.  Checkerboard artifact free sub-pixel convolution: A note on sub-pixel convolution, resize convolution and convolution resize , 2017, ArXiv.

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

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

[21]  Sebastian Ramos,et al.  The Cityscapes Dataset for Semantic Urban Scene Understanding , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Yann LeCun,et al.  Stacked What-Where Auto-encoders , 2015, ArXiv.

[23]  Kibok Lee,et al.  Augmenting Supervised Neural Networks with Unsupervised Objectives for Large-scale Image Classification , 2016, ICML.

[24]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Yash Patel,et al.  Human Perceptual Evaluations for Image Compression , 2019, ArXiv.

[26]  R. Manmatha,et al.  Deep Perceptual Compression , 2019, ArXiv.

[27]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[28]  Tim Fingscheidt,et al.  GAN- vs. JPEG2000 Image Compression for Distributed Automotive Perception: Higher Peak SNR Does Not Mean Better Semantic Segmentation , 2019, ArXiv.