Lossless image compression is required in various applications to reduce storage or transmission costs of images, while requiring the reconstructed images to have zero information loss compared to the original. Existing lossless image compression methods either have simple design but poor compression performance, or complex design, better performance, but with no performance guarantees. In our endeavor to develop a lossless image compression method with low complexity and guaranteed performance, we argue that compressibility of a color image is essentially derived from the patterns in its spatial structure, intensity variations, and color variations. Thus, we divide the overall design of a lossless image compression scheme into three parts that exploit corresponding redundancies. We further argue that the binarized version of an image captures its fundamental spatial structure. In this first part of our work, we propose a scheme for lossless compression of binary images.
The proposed scheme first learns dictionaries of $16\times16$, $8\times8$, $4\times4$, and $2\times 2$ square pixel patterns from various datasets of binary images. It then uses these dictionaries to encode binary images. These dictionaries have various interesting properties that are further exploited to construct an efficient and scalable scheme. Our preliminary results show that the proposed scheme consistently outperforms existing conventional and learning based lossless compression approaches, and provides, on average, as much as $1.5\times$ better performance than a common general purpose lossless compression scheme (WebP), more than $3\times$ better performance than a state of the art learning based scheme, and better performance than a specialized scheme for binary image compression (JBIG2).
ETH Zurich（苏黎世联邦理工学院）；Google Research, Brain Team（谷歌研究院（大脑团队））
We leverage the powerful lossy image compression algorithm BPG to build a lossless image compression system. Specifically, the original image is first decomposed into the lossy reconstruction obtained after compressing it with BPG and the corresponding residual. We then model the distribution of the residual with a convolutional neural network-based probabilistic model that is conditioned on the BPG reconstruction, and combine it with entropy coding to losslessly encode the residual. Finally, the image is stored using the concatenation of the bitstreams produced by BPG and the learned residual…
We introduce a simple and efficient lossless image compression algorithm. We store a low resolution version of an image as raw pixels, followed by several iterations of lossless super-resolution. For lossless super-resolution, we predict the probability of a high-resolution image, conditioned on the low-resolution input, and use entropy coding to compress this super-resolution operator. Super-Resolution based Compression (SReC) is able to achieve state-of-the-art compression rates with practical runtimes on large datasets. Code is available online at https://github.com/caoscott/SReC.
We make the following striking observation: fully convolutional VAE models trained on 32x32 ImageNet can generalize well, not just to 64x64 but also to far larger photographs, with no changes to the model. We use this property, applying fully convolutional models to lossless compression, demonstrating a method to scale the VAE-based 'Bits-Back with ANS' algorithm for lossless compression to large color photographs, and achieving state of the art for compression of full size ImageNet images. We release Craystack, an open source library for convenient prototyping of lossless compression using pr…
Waseda University（早稻田大学）；Waseda Research Institute for Science and Engineering（早稻田大学科学与工程研究院）
Lossless image compression is an essential research field in image compression. Recently, learning-based image compression methods achieved impressive performance compared with traditional lossless methods, such as WebP, JPEG2000, and FLIF. However, there are still many impressive lossy compression methods that can be applied to lossless compression. Therefore, in this paper, we explore the methods widely used in lossy compression and apply them to lossless compression. Inspired by the impressive performance of the Gaussian mixture model (GMM) shown in lossy compression, we generate a lossless…
Microarray technology is a new and powerful tool for the concurrent monitoring of a large number of gene expressions. Each microarray experiment produces hundreds of images. Each digital image requires a large storage space. Hence, real-time processing of these images and transmission of them necessitates efficient and custom-made lossless compression schemes. In this paper, we offer a new architecture for the lossless compression of microarray images. In this architecture, we have used dedicated hardware for the separation of foreground pixels from background ones. By separating these pixels …
Peng Cheng Laboratory（鹏城实验室）；Harbin Institute of Technology（哈尔滨工业大学）；Tsinghua University（清华大学）
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 …
Nokia Technologies（诺基亚科技）；Tampere University（坦佩雷大学）
Lossless image compression is an important technique for image storage and transmission when information loss is not allowed. With the fast development of deep learning techniques, deep neural networks have been used in this field to achieve a higher compression rate. Methods based on pixel-wise autoregressive statistical models have shown good performance. However, the sequential processing way prevents these methods to be used in practice. Recently, multi-scale autoregressive models have been proposed to address this limitation. Multi-scale approaches can use parallel computing systems effic…
We present a CNN-based predictive lossless compression scheme for raw color mosaic images of digital cameras. This specialized application problem was previously understudied but it is now becoming increasingly important, because modern CNN methods for image restoration tasks (e.g., superresolution, low lighting enhancement, deblurring), must operate on original raw mosaic images to obtain the best possible results. The key innovation of this paper is a high-order nonlinear CNN predictor of spatial-spectral mosaic patterns. The deep learning prediction can model highly complex sample dependenc…
In recent years, a bag with image and video compression formats has been torn. However, most of them are focused on lossy compression and only marginally support the lossless mode. In this paper, I will focus on lossless formats and the critical question: "Which one is the most efficient?" It turned out that FLIF is currently the most efficient format for lossless image compression. This finding is in contrast to that FLIF developers stopped its development in favor of JPEG XL.
Unviersity of Science and Technology of China（中国科学技术大学）
As a commonly-used image compression format, JPEG has been broadly applied in the transmission and storage of images. To further reduce the compression cost while maintaining the quality of JPEG images, lossless transcoding technology has been proposed to recompress the compressed JPEG image in the DCT domain. Previous works, on the other hand, typically reduce the redundancy of DCT coefficients and optimize the probability prediction of entropy coding in a hand-crafted manner that lacks generalization ability and flexibility. To tackle the above challenge, we propose the learned lossless JPEG…
We propose the first practical learned lossless image compression system, L3C, and show that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000. At the core of our method is a fully parallelizable hierarchical probabilistic model for adaptive entropy coding which is optimized end-to-end for the compression task. In contrast to recent autoregressive discrete probabilistic models such as PixelCNN, our method i) models the image distribution jointly with learned auxiliary representations instead of exclusively modeling the image distribution in RGB space, and ii) only requires …
Takushoku University（拓殖大学）；Tokyo Metropolitan College of Industrial Technology（东京都立产业技术高等专门学校）；Tokyo Metropolitan University（东京都立大学）
An efficient two-layer coding method using the histogram packing technique with the backward compatibility to the legacy JPEG is proposed in this paper. The JPEG XT, which is the international standard to compress HDR images, adopts two-layer coding scheme for backward compatibility to the legacy JPEG. However, this two-layer coding structure does not give better lossless performance than the other existing methods for HDR image compression with single-layer structure. Moreover, the lossless compression of the JPEG XT has a problem on determination of the coding parameters; The lossless perfor…
Isfahan University of Technology（伊斯法罕理工大学）；University of Queensland（昆士兰大学）；University of Michigan（密歇根大学）
Recent advances in capsule endoscopy systems have introduced new methods and capabilities. The capsule endoscopy system, by observing the entire digestive tract, has significantly improved diagnosing gastrointestinal disorders and diseases. The system has challenges such as the need to enhance the quality of the transmitted images, low frame rates of transmission, and battery lifetime that need to be addressed. One of the important parts of a capsule endoscopy system is the image compression unit. Better compression of images increases the frame rate and hence improves the diagnosis process. I…
Peng Cheng Laboratory, Shenzhen, China（鹏城实验室，深圳，中国）；Department of Electrical Engineering, City University of Hong Kong, Hong Kong SAR（香港城市大学电子工程系，香港特别行政区）；Department of Computer Science, City University of Hong Kong, Hong Kong SAR（香港城市大学计算机科学系，香港特别行政区）；School of Computer Science, Peking University, Beijing, China（北京大学计算机学院，北京，中国）
RAWIC: Bit-Depth Adaptive Lossless Raw Image Compression
School of Electronics, Peking University（北京大学电子学院）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Recent learning-based lossless image compression methods encode an image in the unit of subimages and achieve comparable performances to conventional non-learning algorithms. However, these methods do not consider the performance drop in the high-frequency region, giving equal consideration to the low and high-frequency areas. In this paper, we propose a new lossless image compression method that proceeds the encoding in a coarse-to-fine manner to separate and process low and high-frequency regions differently. We initially compress the low-frequency components and then use them as additional …
Tokyo Metropolitan College of Industrial Technology（东京都立产业技术高等专门学校）；Takushoku University（拓殖大学）；Tokyo Metropolitan University（东京都立大学）
We propose an efficient two-layer near-lossless coding method using an extended histogram packing technique with backward compatibility to the legacy JPEG standard. The JPEG XT, which is the international standard to compress HDR images, adopts a two-layer coding method for backward compatibility to the legacy JPEG standard. However, there are two problems with this two-layer coding method. One is that it does not exhibit better near-lossless performance than other methods for HDR image compression with single-layer structure. The other problem is that the determining the appropriate values of…
In this work, we establish an asymptotic limit of almost-lossless compression of a random, finite alphabet tensor which admits a low-rank canonical polyadic decomposition.
There is a special type of text which the order of the rows makes no difference (e.g., a word list). To compress these special texts, the traditional lossless compression method is not the ideal choice. A new method that can achieve better compression results for this type of texts is proposed. The texts are pre-processed by a method named SSE and are then compressed through the traditional lossless compression method. Comparison shows that an improved compression result is achieved.
An alternative approach to two-part 'critical compression' is presented. Whereas previous results were based on summing a lossless code at reduced precision with a lossy-compressed error or noise term, the present approach uses a similar lossless code at reduced precision to establish absolute bounds which constrain an arbitrary lossy data compression algorithm applied to the original data.
It was estimated that the world produced $59 ZB$ ($5.9 \times 10^{13} GB$) of data in 2020, resulting in the enormous costs of both data storage and transmission. Fortunately, recent advances in deep generative models have spearheaded a new class of so-called "neural compression" algorithms, which significantly outperform traditional codecs in terms of compression ratio. Unfortunately, the application of neural compression garners little commercial interest due to its limited bandwidth; therefore, developing highly efficient frameworks is of critical practical importance. In this paper, we dis…
A new binary (bit-level) lossless compression catalyst method based on a modular arithmetic, called Binary Allocation via Modular Arithmetic (BAMA), has been introduced in this paper. In other words, BAMA is for storage and transmission of binary sequences, digital signal, images and video, also streaming and all kinds of digital transmission. As we said, our method does not compress, but facilitates the action of the real compressor, in our case, any lossless compression algorithm (Run Length Encoding, Lempel-Ziv-Welch, Huffman, Arithmetic, etc), that is, it acts as a compression catalyst. Fi…
As a probabilistic modeling technique, the flow-based model has demonstrated remarkable potential in the field of lossless compression \cite{idf,idf++,lbb,ivpf,iflow},. Compared with other deep generative models (eg. Autoregressive, VAEs) \cite{bitswap,hilloc,pixelcnn++,pixelsnail} that explicitly model the data distribution probabilities, flow-based models perform better due to their excellent probability density estimation and satisfactory inference speed. In flow-based models, multi-scale architecture provides a shortcut from the shallow layer to the output layer, which significantly reduce…
UCLA（加州大学洛杉矶分校）；University of California, Irvine（加州大学欧文分校）
Despite extensive progress on image generation, common deep generative model architectures are not easily applied to lossless compression. For example, VAEs suffer from a compression cost overhead due to their latent variables. This overhead can only be partially eliminated with elaborate schemes such as bits-back coding, often resulting in poor single-sample compression rates. To overcome such problems, we establish a new class of tractable lossless compression models that permit efficient encoding and decoding: Probabilistic Circuits (PCs). These are a class of neural networks involving $|p|…
Tsinghua University（清华大学）；Peng Cheng Laboratory（鹏城实验室）；Renmin University of China（中国人民大学）
By applying entropy codecs with learned data distributions, neural compressors have significantly outperformed traditional codecs in terms of compression ratio. However, the high inference latency of neural networks hinders the deployment of neural compressors in practical applications. In this work, we propose Integer-only Discrete Flows (IODF), an efficient neural compressor with integer-only arithmetic. Our work is built upon integer discrete flows, which consists of invertible transformations between discrete random variables. We propose efficient invertible transformations with integer-on…
This article describes a technique of using a trigonometric function and combinatorial calculations to code or transform any finite sequence of binary numbers (0s and 1s) of any length to a unique set of three Real numbers. In reverse, these three Real numbers can be used independently to reconstruct the original Binary sequence precisely. The main principles of this technique are then applied in a proposal for a highly efficient model for Lossless Data Compression.
We develop a simple and elegant method for lossless compression using latent variable models, which we call 'bits back with asymmetric numeral systems' (BB-ANS). The method involves interleaving encode and decode steps, and achieves an optimal rate when compressing batches of data. We demonstrate it firstly on the MNIST test set, showing that state-of-the-art lossless compression is possible using a small variational autoencoder (VAE) model. We then make use of a novel empirical insight, that fully convolutional generative models, trained on small images, are able to generalize to images of ar…
The bits-back argument suggests that latent variable models can be turned into lossless compression schemes. Translating the bits-back argument into efficient and practical lossless compression schemes for general latent variable models, however, is still an open problem. Bits-Back with Asymmetric Numeral Systems (BB-ANS), recently proposed by Townsend et al. (2019), makes bits-back coding practically feasible for latent variable models with one latent layer, but it is inefficient for hierarchical latent variable models. In this paper we propose Bit-Swap, a new compression scheme that generali…
Sparse representation has been widely used in data compression, signal and image denoising, dimensionality reduction and computer vision. While overcomplete dictionaries are required for sparse representation of multidimensional data, orthogonal bases represent one-dimensional data well. In this paper, we propose a data-driven sparse representation using orthonormal bases under the lossless compression constraint. We show that imposing such constraint under the Minimum Description Length (MDL) principle leads to a unique and optimal sparse representation for one-dimensional data, which results…
Generative model based image lossless compression algorithms have seen a great success in improving compression ratio. However, the throughput for most of them is less than 1 MB/s even with the most advanced AI accelerated chips, preventing them from most real-world applications, which often require 100 MB/s. In this paper, we propose PILC, an end-to-end image lossless compression framework that achieves 200 MB/s for both compression and decompression with a single NVIDIA Tesla V100 GPU, 10 times faster than the most efficient one before. To obtain this result, we first develop an AI codec tha…
We propose an information-theoretic framework for phase retrieval. Specifically, we consider the problem of recovering an unknown n-dimensional vector x up to an overall sign factor from m=Rn phaseless measurements with compression rate R and derive a general achievability bound for R. Surprisingly, it turns out that this bound on the compression rate is the same as the one for almost lossless analog compression obtained by Wu and Verdú (2010): Phaseless linear measurements are as good as linear measurements with full phase information in the sense that ignoring the sign of m measurements only…
University College London（伦敦大学学院）；University of Edinburgh（爱丁堡大学）
We generalize the 'bits back with ANS' method to time-series models with a latent Markov structure. This family of models includes hidden Markov models (HMMs), linear Gaussian state space models (LGSSMs) and many more. We provide experimental evidence that our method is effective for small scale models, and discuss its applicability to larger scale settings such as video compression.
Challenges and Solutions in Selecting Optimal Lossless Data Compression Algorithms
Department of Computer Science and Engineering（计算机科学与工程系）；East West University（东西方大学）；Bangladesh University of Business and Technology (BUBT)（孟加拉国商业技术大学）
We consider the problem of lossless compression of binary trees, with the aim of reducing the number of code bits needed to store or transmit such trees. A lossless grammar-based code is presented which encodes each binary tree into a binary codeword in two steps. In the first step, the tree is transformed into a context-free grammar from which the tree can be reconstructed. In the second step, the context-free grammar is encoded into a binary codeword. The decoder of the grammar-based code decodes the original tree from its codeword by reversing the two encoding steps. It is shown that the re…
Deep latent variable models have seen recent success in many data domains. Lossless compression is an application of these models which, despite having the potential to be highly useful, has yet to be implemented in a practical manner. We present `Bits Back with ANS' (BB-ANS), a scheme to perform lossless compression with latent variable models at a near optimal rate. We demonstrate this scheme by using it to compress the MNIST dataset with a variational auto-encoder model (VAE), achieving compression rates superior to standard methods with only a simple VAE. Given that the scheme is highly am…
City University of Hong Kong（香港城市大学）；National Taiwan University（台湾大学）
Deep-learning-based compressor has received interests recently due to much improved compression ratio. However, modern approaches suffer from long execution time. To ease this problem, this paper targets on cutting down the execution time of deep-learning-based compressors. Building history-dependencies sequentially (e.g., recurrent neural networks) is responsible for long inference latency. Instead, we introduce transformer into deep learning compressors to build history-dependencies in parallel. However, existing transformer is too heavy in computation and incompatible to compression tasks. …
This work is motivated by the necessity to automate the discovery of structure in vast and evergrowing collection of relational data commonly represented as graphs, for example genomic networks. A novel algorithm, dubbed Graphitour, for structure induction by lossless graph compression is presented and illustrated by a clear and broadly known case of nested structure in a DNA molecule. This work extends to graphs some well established approaches to grammatical inference previously applied only to strings. The bottom-up graph compression problem is related to the maximum cardinality (non-bipart…
In this study, we propose a novel scheme for systematic improvement of lossless image compression coders from the point of view of the universal codes in information theory. In the proposed scheme, we describe a generative model class of images as a stochastic model. Using the Bayes codes, we are able to construct a lossless image compression coder which is optimal under the Bayes criterion for a model class described appropriately. Since the compression coder is optimal for the assumed model class, we are able to focus on the expansion of the model class. To validate the efficiency of the pro…
This paper provides an extensive study of the behavior of the best achievable rate (and other related fundamental limits) in variable-length lossless compression. In the non-asymptotic regime, the fundamental limits of fixed-to-variable lossless compression with and without prefix constraints are shown to be tightly coupled. Several precise, quantitative bounds are derived, connecting the distribution of the optimal codelengths to the source information spectrum, and an exact analysis of the best achievable rate for arbitrary sources is given. Fine asymptotic results are proved for arbitrary (…
University of Toronto（多伦多大学）；Vector Institute（向量研究所）；Facebook AI Research（脸书人工智能研究院）；University College London（伦敦大学学院）；University of Oxford（牛津大学）
Latent variable models have been successfully applied in lossless compression with the bits-back coding algorithm. However, bits-back suffers from an increase in the bitrate equal to the KL divergence between the approximate posterior and the true posterior. In this paper, we show how to remove this gap asymptotically by deriving bits-back coding algorithms from tighter variational bounds. The key idea is to exploit extended space representations of Monte Carlo estimators of the marginal likelihood. Naively applied, our schemes would require more initial bits than the standard bits-back coder,…
Secure distributed data compression in the presence of an eavesdropper is explored. Two correlated sources that need to be reliably transmitted to a legitimate receiver are available at separate encoders. Noise-free, limited rate links from the encoders to the legitimate receiver, one of which can also be perfectly observed by the eavesdropper, are considered. The eavesdropper also has its own correlated observation. Inner and outer bounds on the achievable compression-equivocation rate region are given. Several different scenarios involving the side information at the transmitters as well as …
This work proposes lossless and near-lossless compression algorithms for multi-channel biomedical signals. The algorithms are sequential and efficient, which makes them suitable for low-latency and low-power signal transmission applications. We make use of information theory and signal processing tools (such as universal coding, universal prediction, and fast online implementations of multivariate recursive least squares), combined with simple methods to exploit spatial as well as temporal redundancies typically present in biomedical signals. The algorithms are tested with publicly available e…
