Search Results (865)

In response to degraded parking slot markings caused by wear and tear, water accumulation, or occlusion, which significantly impair the perception accuracy and localization robustness of automated parking systems, this paper proposes SlotNet, a lightweight enhancement network. The proposed method incorporates a skeleton-driven adaptive width completion algorithm to mitigate segmentation errors and restore the topological continuity of fractured parking slot lines. The network integrates three lightweight modules: Lightweight Reparameterized VGG (LightRepVGG) for enhancing the extraction of fine-grained structural features via structural reparameterization, Parallel Perceptual Structured Attention—Light (PASA_Light) for multi-scale feature fusion, and Adaptive Decoupled Detect and Segment (AdaDecDS) for anchor-free decoupled detection and segmentation. The experimental results show that SlotNet achieves an inference speed of 65.75 Frames Per Second (FPS). The mask average precision (mask mAP@0.5) reaches 90.2% under an Intersection over Union (IoU) threshold of 0.5, enabling robust completion and accurate detection of degraded parking slot lines. Compared with existing detection, SlotNet achieves a superior balance among accuracy, robustness, and real-time performance, making it suitable for deployment on embedded in-vehicle platforms. Full article

Deep joint source-channel coding (DeepJSCC) has emerged as a promising paradigm for semantic-aware wireless image transmission, achieving strong performance under challenging channel conditions. However, MSE-trained DeepJSCC systems typically achieve high peak signal-to-noise ratio (PSNR) values but suppress high-frequency details, resulting in perceptually blurry reconstructions that fail to capture fine textures and edge information. Existing perceptual enhancement approaches for JSCC systems face significant practical limitations: full transceiver redesign methods require replacing both the transmitter and the receiver with large models (19–31 million parameters), incurring substantial deployment costs; diffusion-based refinement approaches require over 1700 million additional parameters and introduce inference latency exceeding 13 s, rendering them unsuitable for latency-constrained wireless applications; and generic image restoration networks lack channel state awareness and cannot adapt to varying signal-to-noise ratio (SNR) conditions. This paper proposes a lightweight receiver-only perceptual enhancer designed for use with frozen DeepJSCC backbones. The proposed module adopts residual learning with feature-wise linear modulation (FiLM)-based SNR-adaptive modulation to dynamically adjust the enhancement strength under varying channel conditions. A radially weighted FFT magnitude loss is further introduced to guide high-frequency recovery. The enhancer adds only 0.29 million trainable parameters (<1% of the backbone) and requires neither transmitter modification nor backbone retraining. Extensive experiments on the Kodak24 and DIV2K datasets demonstrate a 34.4–37.5% LPIPS reduction over the frozen DeepJSCC baseline under AWGN channels. Supplementary robustness evaluations further show a 30–33% LPIPS reduction under Rayleigh fading, and stable generalization to unseen SNR levels. The receiver-side decoder-plus-enhancer pipeline requires 43 ms at 768 × 512 resolution, corresponding to approximately 23 frames per second. Full article

Low-light image enhancement (LLIE) seeks to improve visibility while suppressing amplified noise, preserving color, and preventing highlight over-enhancement. Most existing methods infer a normally exposed image from a single observed representation, requiring one feature stream to reconcile shadow brightening, highlight protection, denoising, and chromatic correction. We propose VEX, a chroma-stable virtual exposure routing network for single-image LLIE. A Chroma-Stable Virtual Exposure Generator (CVEG) decomposes the input into luminance and log-chroma components and produces five learnable virtual exposure states by perturbing luminance in a bounded space under a shared log-chroma constraint. A shared multi-scale encoder extracts comparable features from all states. At each of four scales, a Noise-Saturation-aware Exposure Router (NSER) combines learned feature evidence with explicit luminance, mid-tone, saturation, and detail-variation priors to predict pixel-wise softmax weights over the exposure states. An Exposure State Mixer (ESM) then performs gated multi-view recalibration of the routed bottleneck, after which a routed-skip decoder predicts a residual correction. VEX therefore casts LLIE as spatially adaptive selection among internal exposure hypotheses rather than as direct single-state regression. Extensive experiments on CDD-11 and LOL demonstrate that VEX consistently outperforms representative traditional and learning-based methods across fidelity, structural, and perceptual criteria. Full article

AI-powered virtual humans are increasingly used as live streaming presenters, yet it remains unclear how consumers translate experiences with these embodied agents into trust and repurchase intention. Rather than tracing a complete multi-stage consumer journey, this study focuses on a recent virtual human live streaming session as a focal touchpoint that compresses product discovery, evaluation, interaction, and purchase support. Integrating consumer touchpoint logic with the Stimulus–Organism–Response (S-O-R) framework, we examine how perceptual touchpoint experience (active control, synchronicity, and two-way communication) and cognitive touchpoint experience (perceived expertise and perceived competence) shape consumer trust and repurchase intention. Using survey data from 305 consumers with virtual human live streaming experience, this study tested the proposed model via partial least squares structural equation modeling (PLS-SEM) and supplemented the findings with fuzzy-set qualitative comparative analysis (fsQCA). The results showed that both perceptual and cognitive touchpoint experiences significantly enhanced trust, which partially mediated their effects on repurchase intention; cognitive touchpoint experience also exerted a strong direct effect on repurchase intention. The fsQCA results revealed two equifinal configurations leading to high repurchase intention: a full-experience path (high perceptual experience + high cognitive experience + high trust) and a capability-dominant path (low perceptual experience + high cognitive experience + high trust). This study contributes to virtual human commerce research by distinguishing interaction-process cues from competence-based source cues and by showing when AI-powered live streaming can support post-touchpoint retention. Full article

Background: Beetroot-derived nitrate supplementation is a widely studied nutritional strategy to enhance athletic performance. Although ergogenic benefits have been reported in recreational and moderately trained individuals, evidence for highly trained and elite athletes remains inconsistent. Objectives: This scoping review aimed to map and synthesize evidence from randomized controlled trials (RCTs) investigating the effects of beetroot-derived nitrate supplementation on performance, recovery, and physiological outcomes in highly trained and elite athletes. Methods: The review followed the Joanna Briggs Institute methodology and PRISMA-ScR guidelines. Literature searches were conducted in PubMed, Scopus, and Web of Science. Eligible studies included RCTs involving McKay Tier 3–5 athletes and evaluating beetroot-derived nitrate supplementation as a standalone intervention. Results: Thirty-one RCTs met the inclusion criteria, representing athletes from a wide range of sports. Supplementation protocols varied substantially, with nitrate doses ranging from 4 to 19.5 mmol·day⁻¹ (248–1209 mg·day⁻¹) and durations from acute administration to 15 days. Positive effects were most frequently reported for cycling time-trial performance, Yo-Yo intermittent recovery performance, anaerobic power, neuromuscular performance, exercise tolerance, and recovery. In contrast, findings for endurance performance, sport-specific skills, oxygen consumption, and perceptual responses were inconsistent despite marked increases in nitrate and nitrite bioavailability. The outcomes seemed to depend on dosage, duration, sport type, and athletes’ training status. Conclusions: Beetroot-derived nitrate supplementation may enhance performance in highly trained and elite athletes, particularly during high-intensity and anaerobic activities. However, the effects are inconsistent, underscoring the need for further research to establish optimal supplementation strategies and evaluate long-term efficacy in elite sporting populations. Full article

Demand for high-quality interactive and real-time rendering remains challenging, as it requires balancing image realism with computational resources. Static parameter tuning of traditional approaches cannot provide adaptive rendering according to the varying complexity of dynamic scenes. This limitation arises from two main deficiencies in existing rendering pipelines: reactive methods that only enhance images after rendering without optimizing the renderer itself, and proactive methods that still rely on manual parameter calibration for each scene. These shortcomings are solved by this paper with an innovative optimization method that is a combination of a genetic algorithm (GA) and artificial neural networks (ANNs). This method offers a closed-loop system that is not found in any other static pipeline. Specifically, in our approach, ANNs will be used to predict the renderer’s initial parameter values from scene descriptor data, such as the number of polygons, lighting, and materials. After predicting the parameters, GA will optimize them based on the fitness value, which is determined by maximizing one objective (perceptual quality, defined by the SSIM measure) and minimizing another (rendering time). Our approach can be easily implemented within standard pipeline frameworks (Autodesk Maya Arnold). Full article

Background/Objectives: Beetroot juice (BRJ), a dietary nitrate source, may enhance high-intensity intermittent exercise, but its effects on single- and repeated-sprint performance remain unclear. This systematic review and meta-analysis aimed to evaluate the effects of BRJ supplementation on sprint-related performance and neuromuscular, perceptual, and physiological outcomes. Methods: PubMed, Scopus, and Web of Science were searched for trials published from 2014 to June 2026. Eligible studies compared BRJ with placebo or control in healthy adults aged 18–40 years. The review followed PRISMA guidelines. Methodological quality and risk of bias were assessed using the PEDro scale and Cochrane RoB 2 tool. Evidence certainty was assessed using GRADE. Standardized mean differences (SMDs) with 95% confidence intervals (CIs) were calculated. Results: Twenty-three randomized trials involving 401 participants were included, and 21 contributed to the meta-analysis. BRJ improved time to peak power in four Wingate-based studies (SMD = −0.92, 95% CI: −1.29 to −0.54, p < 0.001) and handgrip strength (SMD = 0.40, 95% CI: 0.05 to 0.74, p = 0.027). No significant effects were observed for countermovement jump, peak or mean power, 10 m or 20 m sprint performance, perceived exertion, heart rate, or blood lactate. Sex did not significantly moderate the effects, although female data were limited. Certainty was low for most outcomes and very low for 20 m sprint performance and blood lactate. Conclusions: BRJ may improve time to peak power and handgrip strength; however, low- to very-low-certainty evidence does not support its routine use to enhance short-distance or repeated-sprint performance. Full article

Unlike natural image deblurring, which primarily emphasizes perceptual quality and pixel-level fidelity, Quick Response (QR) code deblurring must retain decoding-critical structures to guarantee successful decoding. QR codes contain regular binary module grids and functional patterns with sharp boundaries, providing a strong structural prior for restoration. However, most existing learning-based QR restoration methods capture QR-specific structural information via implicit feature learning. To address this limitation, we propose an Edge-Guided Attention Block (EGAB), which explicitly extracts multi-directional edge priors and injects them into the query–key correlations of Transformer attention. Based on EGAB, we develop an Edge-Guided Restormer (EG-Restormer) for restoring severely blurred QR codes. For mildly blurred inputs, we introduce a Lightweight and Efficient Network (LENet) that performs fast restoration with low computational overhead. We further integrate EG-Restormer and LENet into an Adaptive Dual-network (ADNet), which selects the appropriate restoration branch according to the input blur level. Extensive experiments demonstrate the effectiveness of the proposed framework. EG-Restormer boosts the decoding rate by 8.67 percentage points under GoPro-only training and achieves the highest decoding rate among the evaluated methods after QRData fine-tuning. Moreover, ADNet reduces average inference latency by 19% while maintaining comparable decoding performance. These results suggest that explicit edge prior modeling enhances the recovery of structures critical for decoding, while adaptive routing provides an effective balance between decoding accuracy and computational efficiency. Full article

Despite substantial AI technology investment, many firms fail to translate isolated AI applications into integrated capabilities that deliver strategic returns and drive business model changes. Grounded in service-dominant logic (SDL), this study proposes and empirically tests a theoretical framework that positions AI capability (AIC) as a key antecedent in the nomological network of business model innovation (BMI). Drawing on a three-wave, two-week-interval longitudinal survey of 193 Chinese digital-intensive firms across IT, technical services, and digital leasing industries, and employing PLS-SEM, we examine associations among focal constructs, specifically, the mediating role of customer responsiveness (CR) and the moderating effect of digital organizational culture (DOC). This design mitigates common method bias and establishes temporal causal ordering. Empirical results indicate that AIC positively relates to BMI both directly and indirectly through CR, and that DOC significantly enhances the indirect effect of AIC on BMI via CR, particularly under high levels of AI-enabled sensing and interpretation. However, causal inference is limited by the cross-sectional nature of the data and self-reported measures. This study makes three key theoretical contributions. First, we identify CR as a market-oriented mechanism linking AIC to BMI, shifting focus from prior internal efficiency-focused mechanisms to customer-centric value co-creation. Second, we extend SDL to the AI context by clarifying how DOC shapes the strategic transformation of ambiguous probabilistic AI outputs into market-oriented actions. Third, we introduce DOC as an internal boundary condition for AIC, complementing prior research on external environmental moderators. These findings provide actionable guidance for managers seeking to unlock the strategic value of AI investments. Findings reflect statistical associations rather than confirmed causal effects, and results are based on perceptual survey data from Chinese digital firms. Full article

Images captured under practical low-light conditions typically suffer from insufficient brightness, color distortion, noise, and blur, and the enhancement process itself may further introduce overexposed highlights. This paper presents HLCNet, an HVI-guided Large-Small Convolutional Cross-Branch Network for low-light restoration. RGB inputs are transformed into the HVI space so that chromatic and intensity information can be enhanced in two complementary branches. Each branch applies LSConv to couple broad illumination context with local structural modeling, followed by SE channel recalibration and an LCA-based encoder–decoder, while a soft overexposure constraint suppresses excessive responses without hard clipping. To ensure a controlled comparison, CIDNet is reproduced in the same Tesla T4 environment, whereas the published CIDNet results and other previously reported values are explicitly marked as external references. On LOL-Blur, HLCNet raises the PSNR of the reproduced CIDNet baseline from 26.5438 dB to 27.6260 dB, increases the SSIM from 0.8839 to 0.8863, and reduces the LPIPS from 0.1224 to 0.1056. On LOL-v2 Real and Synthetic, it attains 23.843 dB and 25.991 dB PSNR, respectively. Ablation, sensitivity, qualitative, and perceptual color-space analyses indicate that HLCNet is particularly effective for low-light images containing blur and weak structural details. Full article

Restoring images captured in low-light rainy scenes is challenging because brightness degradation and rain corruption are strongly coupled. Enhancing visibility may amplify hidden rain streaks and noise, whereas aggressive deraining can suppress already weak scene structures. Existing cascaded pipelines and general restoration models often struggle to handle this interaction effectively. In this paper, we present the Degradation-Robust Hue Prior Network (DHP-Net), a single-stage framework for low-light rainy image restoration that combines degradation-robust hue prior guidance with perturbation-aware feature modulation. Specifically, DHP-Net extracts multi-scale hue priors to provide stable structural and color cues under coupled degradations, and it injects them into a hierarchical Transformer restoration backbone. To further improve interaction among entangled feature responses, we introduce a Channel-adaptive Attention Perturbation Module that reorganizes intermediate representations before cross-channel aggregation. In this way, the proposed model jointly promotes visibility enhancement, rain removal, and structure preservation within a unified architecture. Extensive experiments on the Low-Light Rain (LLR) benchmark show that DHP-Net achieves 33.14 dB Peak Signal-to-Noise Ratio (PSNR) and 0.9252 Structural Similarity Index Measure (SSIM) on synthetic data and also delivers superior perceptual quality on real-world low-light rainy images, consistently outperforming existing state-of-the-art restoration models. Full article

Infrared imaging has unique advantages in remote sensing observation and non-contact measurement, but its inherent low contrast and blurred structural details limit the reliability of scene interpretation by human observers. Unlike deep learning-based approaches that rely on data-driven training and substantial computational resources, we propose a Hybrid Prior Enhanced Decomposition (HPED) model, a training-free, model-driven framework that incorporates structural and luminance priors into a multi-stage enhancement pipeline. An l₁–l₀-regularized decomposition separates the input into a base layer that preserves global structures and salient edges and a detail layer in which low-amplitude fluctuations and noise are suppressed. A prior-preserving bi-gamma correction method enhances base-layer contrast through prior-guided histogram segmentation and adaptive gray-level redistribution. An improved grayscale mapping strategy further enhances global contrast while maintaining interframe consistency. Experiments on real SWIR, MWIR, and LWIR images show that HPED ranks first among evaluated traditional and deep learning-based methods on key perceptual quality metrics (SSIM, VIF, LIF), while achieving over 25 fps on a CPU-only platform, sufficient for smooth real-time visual display. Task-oriented evaluation further shows that the HPED improves CNR and SCR by 174.7 ± 11.4% and 298.5 ± 52.1% on average over the raw input, outperforming all competing methods and suggesting potential applicability in downstream machine perception tasks such as detection and tracking. Full article

We propose an adaptive image enhancement method based on photometric statistics to improve object detection under adverse illumination conditions. Conventional image enhancement methods primarily target perceptual quality and may alter recognition-relevant features, potentially degrading detection performance. In contrast, the proposed method adaptively determines the enhancement intensity by combining a predefined domain-specific preset with a photometric risk score calculated from the photometric statistics of the input image to estimate the risk of enhancement-induced photometric risks. Based on these estimates, the enhancement intensity is adaptively controlled, and unnecessary transformation is conditionally bypassed. Experiments on the Berkeley DeepDrive 100K dataset using YOLOv11 demonstrate that the proposed method improves F1-score and mean Average Precision by 0.101 and 0.195, respectively, compared with unprocessed images under adverse conditions, including low-light environments. These results demonstrate that detector-oriented adaptive enhancement can improve robustness while reducing performance degradation caused by unnecessary or excessive image transformation. Full article

Indigenous grains, such as pearl millet, can contribute to alleviating food insecurity in South Africa and addressing the health and well-being of consumers. Stigmatisation and a lack of consumer knowledge about indigenous grains have been found to stifle the consumption of these grains. Therefore, this study aimed to explore South African consumers’ perceived understanding and experience of pearl millet and the external product attributes that attract their attention and steer them towards purchasing and consuming this indigenous grain. This interpretivist phenomenological exploratory study used a qualitative methodology. Small synchronous online focus groups were used to gather the data. The thematic analyses revealed that consumers are generally perceived as uncertain about and lacking experience in the use and consumption of pearl millet, which results from factors such as product unfamiliarity, a lack of knowledge, the product being overlooked in stores, and various assumptions about the grain. Consumers’ perceived willingness to purchase pearl millet may be influenced by several product attraction indicators, including price, packaging, whether it is produced locally, retailer image, and quality-enhancement attributes, which marketers and product developers in South Africa should use to grow consumer interest. This study contributes towards changing the consumer perceived approach to pearl millet by identifying the factors that hamper and limit the choice of pearl millet consumption. South Africa can ill afford to neglect marketing and improving consumer awareness of pearl millet if the health and well-being of South African consumers are to be improved. Full article

Despite rapid advances in laser display technology, existing evaluation frameworks remain confined to isolated physical metrics, decoupled from human visual perception. This study presents the laser display comprehensive testing system (LD-CTS003), a unified platform integrating physical characterization and visual perceptual assessment. Grounded in opponent-process theory, the system implements a complete color conversion pipeline from display RGB through CIE XYZ and LMS to the Derrington–Krauskopf–Lennie space, linking spectral output to retinal cone responses. The hardware architecture features five-axis precision motion and multi-sensor synchronous acquisition, while the software supports both conventional optical measurements and psychophysical experiments. Static image resolution was evaluated via stripe-pattern modulation analysis across viewing distances, and visual contrast sensitivity was measured using Gabor stimuli under varying luminance and eccentricity. The results demonstrate that reduced viewing distances enhance effective resolution, with text display imposing stricter requirements than image display. Contrast sensitivity functions exhibit band-pass profiles, with luminance and eccentricity strongly modulating achromatic and red–green channels, whereas yellow–violet responses remain relatively robust peripherally. By unifying objective metrology and subjective evaluation, this work establishes a perception-oriented framework for laser display quality assessment, providing a physiologically grounded foundation for display optimization and standard development. Full article