The demand for data storage has been growing exponentially over the past decades. Current techniques have significant shortcomings, such as high resource requirements and a lack of sufficient longevity. In contrast, research on DNA-based storage has been advancing notably due to its low environmental impact, larger capacity, and longer lifespan. This led to the development of compression methods that adapted the binary representation of legacy JPEG images into a quaternary base of nucleotides following the biochemical constraints of current synthesis and sequencing mechanisms. In this work, we show that DNA can also be leveraged to efficiently store images compressed with neural networks even without retraining, by combining a convolutional autoencoder with a Goldman encoder. The proposed method is compared to the state of the art, resulting in higher compression efficiency on two different datasets when evaluated by a number of objective quality metrics.
Recent advances in image compression made it possible and desirable for image quality to approach the visually lossless range. Nevertheless, the most commonly used subjective visual quality assessment protocols, e.g. the ones reported in ITU-T Rec. BT.500, were found ineffective in evaluating images with visual quality between high to nearly visually lossless. In this context, the JPEG Committee initiated a renewed activity on the Assessment of Image Coding, also referred to as JPEG AIC, aiming at standardizing new subjective and objective image quality assessment methodologies applicable in the quality range from high to nearly visually lossless. For this purpose, a Call for Contributions on Subjective Image Quality Assessment was released with deadline in April 2023, and a Call for Proposals on Objective Image Quality Assessment is expected to be issued in the near future. This paper aims at providing an overview of submissions to the Call for Contributions and presenting the recent advances in this activity, as well as future directions.
In recent years, new emerging immersive imaging modalities, e.g. light fields, have been receiving growing attention, becoming increasingly widespread over the years. Light fields are often captured through multi-camera arrays or plenoptic cameras, with the goal of measuring the light coming from every direction at every point in space. Light field cameras are often sensitive to noise, making light field denoising a crucial pre- and post-processing step. A number of conventional methods for light field denoising have been proposed in the state of the art, making use of the redundant information coming from the different views to remove the noise. While learning-based denoising has demonstrated good performance in the context of image denoising, only preliminary works have studied the benefit of using neural networks to denoise light fields. In this paper, a learning-based light field denoising technique based on a convolutional neural network is investigated by extending a state-of-the-art image denoising method, and taking advantage of the redundant information generated by different views of the same scene. The performance of the proposed approach is compared in terms of accuracy and scalability to state-of-the-art methods for image and light field denoising, both conventional and learning-based. Moreover, the robustness of the proposed method to different types of noise and their strengths is reviewed. To facilitate further research on this topic, the code is made publicly available at https://github.com/mmspg/Light-Field-Denoising
Due to the increasing number of pictures captured and stored every day by and on digital devices, lossy image compression has become inevitable to limit the needed storage requirement. As a consequence, these compression methods might introduce some visual artifacts, whose visibility depends on the chosen bitrate. Modern applications target images with high to near-visually lossless quality, in order to maximize the visual quality while still reducing storage space consumption. In this context, subjective and objective image quality assessment are essential tools in order to develop compression methods able to generate images with high visual quality. While a large variety of subjective quality assessment protocols have been standardized in the past, they have been found to be imprecise in the quality interval from high to near-visually lossless. Similarly, an objective quality metric designed to work specifically in the mentioned range has not been designed yet. As current quality assessment methodologies have proven to be unreliable, a renewed activity on the Assessment of Image Coding, also referred to as JPEG AIC, was recently launched by the JPEG Committee. The goal of this activity is to extend previous standardization efforts, i.e. AIC Part 1 and AIC Part 2 (also know as AIC-1 and AIC-2), by developing a new standard, known as AIC Part 3 (or AIC-3). Notably, the goal of the activity is to standardize both subjective and objective visual quality assessment methods, specifically targeting images with quality in the range from high to near-visually lossless. Two Draft Calls for Contributions on Subjective Image Quality Assessment1, 2 were released, aiming at collecting contributions on new methods and best practices for subjective image quality assessment in the target quality range, while a Call for Proposals on Objective Image Quality Assessment is expected to be released at a later date. This paper aims at summarizing past JPEG AIC efforts and reviewing the main objectives of the future activities, outlining the scope of the activity, the main use cases and requirements, and call for contributions. Finally, conclusions on the activity are drawn.
Noise is an intrinsic part of any sensor and is present, in various degrees, in any content that has been captured in real life environments. In imaging applications, several pre- and post-processing solutions have been proposed to cope with noise in captured images. More recently, learning-based solutions have shown impressive results in image enhancement in general, and in image denoising in particular. In this paper, we review multiple novel solutions for image denoising in the compressed domain, by integrating denoising operations into the decoder of a learning-based compression method. The paper starts by explaining the advantages of such an approach from different points of view. We then describe the proposed solutions, including both blind and non-blind methods, comparing them to state of the art methods. Finally, conclusions are drawn from the obtained results, summarizing the advantages and drawbacks of each method.
DNA is an excellent medium for efficient storage of information. Not only it offers a long-term and robust mechanism but also it is environmental friendly and has an unparalleled storage capacity, However, the basic elements in DNA are quaternary, and therefore there is a need for efficient coding of information in quaternary representation while taking into account various biochemical constraints involved. Such constraints create additional complexity on how information should be represented in quaternary code. In this paper, an efficient solution for the storage of JPEG compressed images is proposed. The focus on JPEG file format is motivated by the fact that it is a popular representation of digital pictures. The proposed approach converts an already coded image in JPEG format to a counterpart represented in quaternary representation while taking into account the intrinsic structure of the former. The superiority of the proposed approach is demonstrated by comparing its rate distortion performance to two alternative approaches, namely, a direct transcoding of the binary JPEG compressed file into a quaternary codestream without taking into account its underlying structure, and a complete JPEG decoding followed by an image encoding for DNA storage.
Learning-based image coding has shown promising results during recent several years. Unlike the traditional approaches for image compression, learning-based codecs exploit deep neural networks for reducing dimensionality of the input at the stage where a linear transform would be typically applied previously. The signal representation after this stage, called latent space, caries the information in such a format that it can be interpreted by other deep neural networks without the need of decoding it. One of the tasks that can benefit from the above-mentioned possibility is super resolution. In this paper, we explore the possibilities and propose an approach for super resolution that is applied in the latent space. We focus on two types of architectures: fixed compression model and enhanced compression model. Additionally, we assess the performance of the proposed solutions.
Learning-based approaches to image compression have demonstrated comparable, or even superior performance when compared to conventional approaches in terms of compression efficiency and visual quality. A typical approach in learning-based image compression is through autoencoders, which are architectures consisting of two main parts: a multi-layer neural network encoder and a dual decoder. The encoder maps the input image in the pixel domain to a compact representation in a latent space. Consequently, the decoder reconstructs the original image in the pixel domain from its latent representation, as accurately as possible. Traditionally, image processing algorithms, and in particular image denoising, are applied to the images in the pixel domain before compression, and eventually even after decompression. The combination of the denoising operation with the encoder might reduce the computational cost while achieving the same performance in accuracy. In this paper, the idea of fusing the image denoising operation with the encoder is examined. The results are evaluated both by simulating the human perspective through objective quality metrics, and by machine vision algorithms for the use case of face detection.
Lossy image compression algorithms are usually employed to reduce the storage space required by the large number of digital pictures that are acquired and stored daily on digital devices. Despite the gain in storage space, these algorithms might introduce visible distortions on the images. However, users typically value the visual quality of digital media and do not tolerate any distortion. Objective image quality assessment metrics propose to predict the amount of such distortions as perceived by human subjects, but a limited number of studies have been devoted to the objective assessment of the visibility of artifacts on images as seen by human subjects. In other words, most objective quality metrics do not indicate when the artifacts become imperceptible to human observers. An objective image quality metric that assesses the visibility of artifacts could, in fact, drive the compression methods toward a visually lossless approach. In this paper, we present a subjective image quality assessment dataset, designed for the problem of visually lossless quality evaluation for image compression. The distorted images have been labeled, after a subjective experiment held with crowdsourcing, with the probability of the artifact to be visible to human observers. In contrast to other datasets in the state of the art, the proposed dataset contains a big number of images along with multiple distortions, making it suitable as a training set for a learning-based approach to objective quality assessment.
JPEG image coding standard has been a dominant format in a wide range of applications in soon three decades since it has been released as an international standard. The landscape of applications and services based on pictures has evolved since the original JPEG image coding algorithm was designed. As a result of progress in the state of the art image coding, several alternative image coding approaches have been proposed to replace the legacy JPEG with mixed results. The majority among them have not been able to displace the unique position that the legacy JPEG currently occupies as the ubiquitous image coding format of choice. Those that have been successful, have been so in specific niche applications. In this paper, we analyze why all attempts to replace JPEG have been limited so far, and discuss additional features other than compression efficiency that need to be present in any modern image coding algorithm to increase its chances of success. Doing so, we compare rate distortion performance of state of the art conventional and learning based image coding, in addition to other desired features in advanced multimedia applications such as transcoding. We conclude the paper by highlighting the remaining challenges that need to be overcome in order to design a successful future generation image coding algorithm.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.