1,041 Hits in 2.4 sec

Lossy Image Compression with Compressive Autoencoders [article]

Lucas Theis, Wenzhe Shi, Andrew Cunningham, Ferenc Huszár
2017 arXiv   pre-print
We propose a new approach to the problem of optimizing autoencoders for lossy image compression.  ...  This is in contrast to previous work on autoencoders for compression using coarser approximations, shallower architectures, computationally expensive methods, or focusing on small images.  ...  DISCUSSION We have introduced a simple but effective way of dealing with non-differentiability in training autoencoders for lossy compression.  ... 
arXiv:1703.00395v1 fatcat:ftno22l3tvbhthllmgomabdxtq

DRASIC: Distributed Recurrent Autoencoder for Scalable Image Compression [article]

Enmao Diao, Jie Ding, Vahid Tarokh
2019 arXiv   pre-print
The proposed architecture, which we refer to as Distributed Recurrent Autoencoder for Scalable Image Compression (DRASIC), is able to train distributed encoders and one joint decoder on correlated data  ...  We propose a new architecture for distributed image compression from a group of distributed data sources.  ...  Image compression with Deep Learning There exist a variety of classical codecs for lossy image compression.  ... 
arXiv:1903.09887v3 fatcat:pggenmvw65cvvinu5fo2eh4wmy

Lossy Image Compression with Compressive Autoencoders [article]

Ferenc Huszar, Lucas Theis, Wenzhe Shi, Andrew Cunningham, Apollo-University Of Cambridge Repository, Apollo-University Of Cambridge Repository
We propose a new approach to the problem of optimizing autoencoders for lossy image compression.  ...  This is in contrast to previous work on autoencoders for compression using coarser approximations, shallower archi- tectures, computationally expensive methods, or focusing on small image.  ...  DISCUSSION We have introduced a simple but effective way of dealing with non-differentiability in training autoencoders for lossy compression.  ... 
doi:10.17863/cam.51995 fatcat:x26aq5i5wvfhtk5mgd4uxwhily

Image Compression Using Deep Learning: Methods and Techniques

Arwa Sahib Abd-Alzhra, Mohammed S. H. Al- Tamimi
2022 Iraqi Journal of Science  
Image compression generally represents the significant image information compactly with a smaller size of bytes while insignificant image information (redundancy) already been removed for this reason image  ...  As a result, it is hard to find and recover a well-compressed representation for images, and it also hard to design and test networks that are able to recover images successfully in a lossless or lossy  ...  In the training of AutoEncoders for lossy compression, an easy but efficient way of dealing with non-differentiability was implemented.  ... 
doi:10.24996/ijs.2022.63.3.34 fatcat:43hnfu33krahrarvnab4ul3rq4

Lossy Medical Image Compression using Residual Learning-based Dual Autoencoder Model [article]

Dipti Mishra, Satish Kumar Singh, Rajat Kumar Singh
2021 arXiv   pre-print
In this work, we propose a two-stage autoencoder based compressor-decompressor framework for compressing malaria RBC cell image patches.  ...  The proposed residual-based dual autoencoder network is trained to extract the unique features which are then used to reconstruct the original image through the decompressor module.  ...  The proposed framework reports to be a good ROI based lossy compression scheme, producing good quality images with minimum information loss.  ... 
arXiv:2108.10579v1 fatcat:2no5y3hvnvf4tbu3zyawmua4vq

Neural Multi-scale Image Compression [article]

Ken Nakanishi, Shin-ichi Maeda, Takeru Miyato, Daisuke Okanohara
2018 arXiv   pre-print
This study presents a new lossy image compression method that utilizes the multi-scale features of natural images.  ...  Our model consists of two networks: multi-scale lossy autoencoder and parallel multi-scale lossless coder.  ...  In this work, we are concerned with lossy compression tasks for natural images. JPEG has been widely used for lossy image compression.  ... 
arXiv:1805.06386v1 fatcat:ckcn26gqxbddxb2zm2vsyipesm

Exploring Autoencoder-based Error-bounded Compression for Scientific Data [article]

Jinyang Liu, Sheng Di, Kai Zhao, Sian Jin, Dingwen Tao, Xin Liang, Zizhong Chen, Franck Cappello
2022 arXiv   pre-print
To address this issue, we explore using convolutional autoencoders to improve error-bounded lossy compression for scientific data, with the following three key contributions. (1) We provide an in-depth  ...  Autoencoder (AE) models have been widely used in image compression, but few AE-based compression approaches support error-bounding features, which are highly required by scientific applications.  ...  Several existing lossy image compression autoencoder models [35] , [37] - [39] , [51] , [52] have leveraged GDN and proved its advantages.  ... 
arXiv:2105.11730v6 fatcat:vqt2evw6unbeppdrwcidnjirj4

Image Compression and Actionable Intelligence With Deep Neural Networks [article]

Matthew Ciolino
2022 arXiv   pre-print
We investigate four techniques to aid in the reduction of delivered information: traditional image compression, neural network image compression, object detection image cutout, and image to caption.  ...  To address this, we propose a survey of information reduction techniques to deliver the information from a satellite image in a smaller package.  ...  For example, lossy methods like JPG, object detection, image to caption, and an autoencoder lose information about the image.  ... 
arXiv:2203.13686v2 fatcat:h34v4ek6l5htbdd2cf336ghpaq

A Hybrid Compression Method for Medical Images Based on Region of Interest Using Artificial Neural Networks

Ali Ibrahim Khaleel, Nik Adilah Hanin Zahri, Muhammad Imran Ahmad, Paolo Castaldo
2021 Journal of Engineering  
In this study, a new compression method is proposed for medical images based on convolutional neural networks.  ...  Hence, the storage space and bandwidths required to store and communicate these images are exponentially increasing, which has brought attention toward compressing these images.  ...  [7] uses a hybrid compression method, near-lossless compression for the ROI, and lossy compression for the remainder of the image.  ... 
doi:10.1155/2021/8292396 fatcat:sm7y5zooqjgsboe3rjhvm2tcha

Impact of Misclassification Rates on Compression Efficiency of Red Blood Cell Images of Malaria Infection Using Deep Learning

Yuhang Dong, W. David Pan, Dongsheng Wu
2019 Entropy  
Specifically, we investigate a practical approach where images are first classified before being compressed using stacked autoencoders.  ...  Malaria is a severe public health problem worldwide, with some developing countries being most affected.  ...  In the literature, existing work on deep learning for image compression is fairly sparse, mostly with the goal of achieving low bit rates and higher visual quality for lossy compression.  ... 
doi:10.3390/e21111062 fatcat:mizqfdcv5vhy7e5lg537z3fdda

Lossy Image Compression with Normalizing Flows [article]

Leonhard Helminger, Abdelaziz Djelouah, Markus Gross, Christopher Schroers
2020 arXiv   pre-print
To the best of our knowledge, this is the first work to explore the opportunities for leveraging normalizing flows for lossy image compression.  ...  However, state-of-the-art solutions for deep image compression typically employ autoencoders which map the input to a lower dimensional latent space and thus irreversibly discard information already before  ...  In this work, we propose to leverage normalizing flows as generative models in lossy image compression instead of autoencoders.  ... 
arXiv:2008.10486v1 fatcat:lp7sevbzxbak7fk2onaqf3eepm

Fully Convolutional Model for Variable Bit Length and Lossy High Density Compression of Mammograms [article]

Aupendu Kar, Sri Phani Krishna Karri, Nirmalya Ghosh, Ramanathan Sethuraman, Debdoot Sheet
2018 arXiv   pre-print
Inspired by the reprise of deep learning based compression for natural images over the last two years, we propose a fully convolutional autoencoder for diagnostically relevant feature preserving lossy  ...  Early works on medical image compression date to the 1980's with the impetus on deployment of teleradiology systems for high-resolution digital X-ray detectors.  ...  Related work Information compression in digital media including images can typically be grouped into lossless or lossy.  ... 
arXiv:1805.06909v1 fatcat:dmfs4gwpijhgzgb5ksv5mhy7dm

An Autoencoder-based Learned Image Compressor: Description of Challenge Proposal by NCTU [article]

David Alexandre, Chih-Peng Chang, Wen-Hsiao Peng, Hsueh-Ming Hang
2019 arXiv   pre-print
We propose a lossy image compression system using the deep-learning autoencoder structure to participate in the Challenge on Learned Image Compression (CLIC) 2018.  ...  Our autoencoder uses the residual blocks with skip connections to reduce the correlation among image pixels and condense the input image into a set of feature maps, a compact representation of the original  ...  Introduction Lossy image compression has been a challenging topic in deep learning domain in recent years.  ... 
arXiv:1902.07385v1 fatcat:mfssjegzifdb5lrdb3qvdsbjuq

ANFIC: Image Compression Using Augmented Normalizing Flows

Yung-Han Ho, Chih-Chun Chan, Wen-Hsiao Peng, Hsueh-Ming Hang, Marek Domanski
2021 IEEE Open Journal of Circuits and Systems  
INDEX TERMS Learning-based image compression, flow-based image compression, augmented normalizing flows, perceptually lossless image compression, variable rate image compression.  ...  In particular, ANFIC achieves the state-of-the-art performance, when extended with conditional convolution for variable rate compression with a single model.  ...  However, one issue with most VAE-based schemes is that the autoencoder is generally lossy.  ... 
doi:10.1109/ojcas.2021.3123201 fatcat:bkmilrtm2bgtdbx64d6hbqamoa

Sparse MP4

Daniel A. Wang, Charles M. S. Strauss, Jacob M. Springer, Austin Thresher, Howard Pritchard, Garrett T. Kenyon
2020 2020 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI)  
We report that when compared with standard MP4 tuned for a similar overall compression ratio, Sparse MP4 achieves significantly higher PSNR and similar SSIM scores.  ...  MP4 is currently the gold standard for video compression.  ...  JPEG is a commonly used lossy format for image compression while MP4 is the international standard for compressing video images [1] .  ... 
doi:10.1109/ssiai49293.2020.9094593 dblp:conf/ssiai/WangSSTPK20 fatcat:gk66au2l5nhzngadsiblepubp4
« Previous Showing results 1 — 15 out of 1,041 results