Explore the vast range of titles available.

Over the past few years, deep neural models have made considerable advances in image quality assessment (IQA). However, the underlying reasons for their success remain unclear, owing to the complex nature of deep neural networks. IQA aims to describe how the human visual system (HVS) works and to create its efficient approximations. On the other hand, Saliency Prediction task aims to emulate HVS via determining areas of visual interest. Thus, we believe that saliency plays a crucial role in human perception. In this work, we conduct an empirical study that reveals the relation between IQA and Saliency Prediction tasks, demonstrating that the former incorporates knowledge of the latter. Moreover, we introduce a novel SACID dataset of saliency-aware compressed images and conduct a large-scale comparison of classic and neural-based IQA methods. All supplementary code and data will be available at the time of publication.

Diffusion-based models have recently transformed conditional image generation, achieving unprecedented fidelity in generating photorealistic and semantically accurate images. However, consistently generating high-quality images remains challenging, partly due to the lack of mechanisms for conditioning outputs on perceptual quality. In this work, we propose methods to integrate image quality assessment (IQA) models into diffusion-based generators, enabling quality-aware image generation. First, we experiment with gradient-based guidance to optimize image quality directly and show this approach has limited generalizability. To address this, we introduce IQA-Adapter, a novel architecture that conditions generation on target quality levels by learning the relationship between images and quality scores. When conditioned on high target quality, IQA-Adapter shifts the distribution of generated images towards a higher-quality subdomain. This approach achieves up to a 10% improvement across multiple objective metrics, as confirmed by a subjective study, while preserving generative diversity and content. Additionally, IQA-Adapter can be used inversely as a degradation model, generating progressively more distorted images when conditioned on lower quality scores. Our quality-aware methods also provide insights into the adversarial robustness of IQA models, underscoring the potential of quality conditioning in generative modeling and the importance of robust IQA methods.

In the rapidly progressing field of generative models, the development of efficient and high-fidelity text-to-image diffusion systems represents a significant frontier. This study introduces YaART, a novel production-grade text-to-image cascaded diffusion model aligned to human preferences using Reinforcement Learning from Human Feedback (RLHF). During the development of YaART, we especially focus on the choices of the model and training dataset sizes, the aspects that were not systematically investigated for text-to-image cascaded diffusion models before. In particular, we comprehensively analyze how these choices affect both the efficiency of the training process and the quality of the generated images, which are highly important in practice. Furthermore, we demonstrate that models trained on smaller datasets of higher-quality images can successfully compete with those trained on larger datasets, establishing a more efficient scenario of diffusion models training. From the quality perspective, YaART is consistently preferred by users over many existing state-of-the-art models.

The paper presents an underwater holographic sensor to study marine particles—a miniDHC digital holographic camera, which may be used as part of a hydrobiological probe for accompanying (background) measurements. The results of field measurements of plankton are given and interpreted, their verification is performed. Errors of measurements and classification of plankton particles are estimated. MiniDHC allows measurement of the following set of background data, which is confirmed by field tests: plankton concentration, average size and size dispersion of individuals, particle size distribution, including on major taxa, as well as water turbidity and suspension statistics. Version of constructing measuring systems based on modern carriers of operational oceanography for the purpose of ecological diagnostics of the world ocean using autochthonous plankton are discussed. The results of field measurements of plankton using miniDHC as part of a hydrobiological probe are presented and interpreted, and their verification is carried out. The results of comparing the data on the concentration of individual taxa obtained using miniDHC with the data obtained by the traditional method using plankton catching with a net showed a difference of no more than 23%. The article also contains recommendations for expanding the potential of miniDHC, its purpose indicators, and improving metrological characteristics.

The paper presents a diagnostic complex for plankton studies using the miniDHC (digital holographic camera). Its capabilities to study the rhythmic processes in plankton ecosystems were demonstrated using the natural testing in Lake Baikal in summer. The results of in situ measurements of plankton to detect the synchronization of collective biological rhythms with medium parameters are presented and interpreted. The most significant rhythms in terms of the correlation of their parameters with medium factors are identified. The study shows that the correlation with water temperature at the mooring site has the greatest significance and reliability. The results are verified with biodiversity data obtained by the traditional mesh method. The experience and results of the study can be used for the construction of a stationary station to monitor the ecological state of the water area through the digitalization of plankton behavior.

A new implementation of a beam-steering transmitarray is proposed based on the tiled array architecture. Each pixel of the transmitarray is manufactured as a standalone unit which can be hard-wired for specific transmission characteristics. A set of complementary units, providing reciprocal phase-shifts, can be assembled in a prescribed spatial phase-modulation pattern to perform beam steering and beam forming in a broad spatial range. A compact circuit model of the tiled unit cell is proposed and characterized with full-wave electromagnetic simulations. Waveguide measurements of a prototype unit cell have been carried out. A design example of a tiled 10 × 10-element 1-bit beam-steering transmitarray is presented and its performance benchmarked against the conventional single-panel, i.e., unibody, counterpart. Prototypes of the tiled and single-panel C-band transmitarrays have been fabricated and tested, demonstrating their close performance, good agreement with simulations and a weak effect of fabrication tolerances. The proposed transmitarray antenna configuration has great potential for fifth-generation (5G) communication systems.

The study shows that the use of a submersible digital holographic camera as part of a multifunctional hardware and software complex allows carrying out in situ measurements of plankton, automating the process of obtaining data on plankton, as well as classifying plankton species up to an order within the specified taxonomic groups. Such automation ensures monitoring expeditionary or stationary research of species diversity and spatial and temporal organization of zooplankton in conjunction with hydrophysical parameters of the medium. This paper presents the full-scale results of vertical profiles and daily measurements of plankton made with the use of the submersible digital holographic camera, as well as the classification of plankton in laboratory and field conditions in the automatic mode. It is shown that within the accomplished version the classification algorithm using the morphological parameter makes it possible to solve the problem quickly (time required to obtain the result is less than 1 second and depends on the number of plankton particles and the frame size of a restored image), however the classification accuracy by orders varies within 50-60%.

The paper presents the results of in situ studies of marine particles of different nature using a submersible digital holographic camera (DHC) during the Arctic expedition. It also describes the features, performance specifications, and possibilities of the DHC and the DHC technology. The DHC technology can be used for noninvasive automatic evaluation of spatial and temporal characteristics of plankton, including the distribution of plankton concentrations. The comparison of quantitative analysis of zooplankton net samples and classification results using the DHC revealed that the error of the DHC classification of mesoplankton at the level of the main systematic orders was about 30%. The results of determining the data on the medium, such as water turbidity, according to the radiation shielding factor (degree) by the particles of the Suspension taxon using the DHC technology are presented; the prospects for studying the size of gas bubbles and their volume content according to the Bubble taxon data are shown. The use of holographic data for in situ point estimates is considered.

Our previous studies showed that the change in the plankton response to light could be an indicator of environmental pollution. This study experimentally reveals that the response of Daphnia magna Straus and Daphnia pulex plankton ensembles to photostimulation depends on the intensity of the attracting light. This makes it difficult to identify the occurrence and change of pollutant concentration. The large variability in the magnitude of the behavioral response is caused by the nonlinear response of plankton ensembles to the intensity of the attractor stimulus. As the intensity of the photostimulation increases, the variability of the phototropic response passes through increase, decrease, and relative stabilization phases. The paper proposes a modification of the photostimulation method—paired photostimulation involving successive exposure to two photostimuli of increasing intensity. The first stimulus stabilizes the behavioral response, while the increase in response to the second stimulus makes it possible to more accurately assess the responsiveness of the plankton ensemble. The paper studies the sensitivity of the method of paired stimulation of the behavioral response of different types of freshwater plankton ensembles: Daphnia magna Straus, Daphnia pulex to the effects of pollutants (potassium bichromate, microplastic). The study demonstrates good reliability and increased sensitivity of this method of detecting changes in environmental toxicity compared to single photostimulation or traditional bioindication through the survival rate of test organisms.

Our earlier studies showed that paired photostimulation allows the detection of pollutants in an aqueous medium according to the behavioral responses of freshwater Crustacea. The first stimulus initiated and stabilized the behavioral response. The increase in response to the second stimulus made it possible to assess the responsiveness of the zooplankton community. This paper studies the validity of this method for the detection of micro- and nanoplastic contamination of saltwater reservoirs according to the behavioral response of Artemia salina and Moina salina crustaceans. The studies were conducted in laboratory conditions using a submersible holographic camera developed by us, which ensures the in situ detection of the concentration and speed of crustaceans in a volume of up to 1 dm3, as well as makes it possible to change the intensity and duration of the attracting light. It was established that the phototropic response of crustaceans decreases in seawater at the cumulative dose of exposure to microplastics—0.15 mg∙dm−3∙h and nanoplastics—0.3 mg∙dm−3∙h. The paired photostimulation reveals the altering effect of micro- and nanoplastics in the saltwater medium no later than 3 h after their appearance, which indicates the promising potential of this method for the alarm response in monitoring the environmental well-being of water bodies.