Search Results (239)

Autonomous parking is one of the most demanding manoeuvres a vehicle can be asked to perform. The available space is small, the margins for error are narrow, and the vehicle must achieve an exact final pose while respecting non-holonomic constraints. A persistent gap between detection and execution yields infeasible trajectories or terminal positioning errors. This systematic review examines how bird’s-eye view (BEV) reconstruction supports each link in the perception–planning–control chain, from slot detection through trajectory generation and manoeuvre execution, and identifies where those links remain weakest. No registered review protocol was used. Between 7 January and 10 February 2026, we retrieved 338 records through a single automated engine (OpenAlex) reaching multiple indexed venues, complemented by manual citation chasing; collection was semi-automated and screening was manual. Seventy-two studies passed eligibility screening, of which 45 provide primary, parking-specific evidence; the remaining 27 are prior surveys or generic methodological contributions retained as background rather than as primary evidence. We included studies addressing BEV reconstruction, slot detection, manoeuvre planning, or control with simulated or experimental validation, and excluded duplicates and works reporting no performance evaluation. The synthesis follows five axes: multi-camera homography-based BEV reconstruction, automatic parking-slot detection, geometric and kinematic modelling, planning in confined spaces, and nonlinear control with explicit constraint handling. Across the 45 primary studies, BEV-based methods are reported to improve geometric consistency and support reliable slot detection, and Hybrid A* combined with NMPC recurs as the most frequently reported route to dynamically feasible trajectories, although no study compares these approaches under identical conditions and no quantitative comparison across studies was performed here. The weakest point of the field is integration: perception and control are rarely coupled in a closed loop, and no standardised evaluation framework has yet gained wide acceptance. Heterogeneity in scenarios, metrics, and sensing configurations limits the strength of the evidence, and modular architectures show gaps in perception–planning–control coupling and reproducible transfer to platforms such as Gazebo. No formal risk-of-bias assessment was performed. Full article

Background/Objectives: We aimed to provide an updated synthesis of the efficacy and ocular safety of subretinal adeno-associated viral (AAV) RPGR gene therapy for retinitis pigmentosa GTPase regulator (RPGR)-associated X-linked retinitis pigmentosa (RPGR-XLRP) and to assess the certainty of the available evidence. Methods: We performed a PROSPERO-registered (CRD420251163589), PRISMA 2020 systematic review and meta-analysis using database and trial-registry searches. The primary microperimetry synthesis was restricted to mesopic Macular Integrity Assessment (MAIA) 68-loci acquisitions; continuous-outcome syntheses were conducted at the cohort level, using observed paired-eye contrasts when available; dose levels were interpreted within clinical programs; and above-maximum-tolerated-dose and peripheral-injection cohorts were reported separately. Random-effects analyses used DerSimonian–Laird models with Hartung–Knapp–Sidik–Jonkman small-sample correction. Risk of bias and certainty were assessed with design-matched tools and Grading of Recommendations Assessment, Development and Evaluation (GRADE). Results: The quantitative synthesis included four trials reported in five publications (128 participants; AAV8, AAV5, and AAV2tYF platforms). Mesopic retinal sensitivity numerically favored treatment, but the pooled differences were not statistically significant at six months (mean difference [MD] +1.11 dB; 95% confidence interval [CI], −0.88 to +3.09) or twelve months (MD +0.97 dB; 95% CI, −3.99 to +5.94). Best-corrected visual acuity showed no statistically significant pooled difference (MD +0.94 letters; 95% CI, −4.97 to +6.85). The six-month ≥10-letter low-luminance responder estimate favored treatment, but was nonsignificant and attenuated by twelve months; no primary pooled efficacy outcome reached significance under small-sample-adjusted inference. Certainty was very low for functional outcomes and low for safety outcomes. Uncontrolled treated-eye proportions were 80.8% for intraocular inflammation, 17.0% for ocular serious adverse events, and 4.3% for central-injection retinal detachment. Conclusions: Current evidence does not establish a clinically actionable functional benefit, although a modest true effect cannot be excluded. Clinically relevant ocular safety signals were observed, but the estimates were uncontrolled and program dependent. Adequately powered randomized trials with standardized functional endpoints, optimized subretinal delivery strategies, and careful within-program dose selection are needed. Full article

Anterior segment optical coherence tomography (AS-OCT) is essential for structural assessment of the anterior eye, yet automated landmark localization remains challenged by pervasive speckle noise, indistinct tissue interfaces, and labor-intensive manual annotation with notable inter-observer variability. This study presents NSE YOLO, an enhanced YOLOv11 framework for high-precision landmark localization in AS-OCT images after implantable collamer lens (ICL) implantation. It integrates a dual-branch NewConv module for multi-scale feature extraction, a dual-additive residual self-attention block (SABlock) to suppress background interference, and a Mamba-based EfficientViMBlock embedded in the C3k2 module to balance global contextual modeling and computational efficiency. Validated on 672 expert-annotated postoperative ICL images from 60 patients, NSE YOLO achieved an mAP@0.5 of 90.7% and mAP@0.5:0.95 of 85.1%, outperforming the YOLOv11 baseline by 5.2% and 6.6% with only 2.86 million parameters. Bland–Altman analysis showed negligible systematic bias and narrow limits of agreement for anterior chamber depth. For iridocorneal angle measurements, directional deviations and wider limits of agreement were observed, with performance approaching the level of inter-observer variability among human annotators. NSE YOLO enables automated quantification of anterior chamber depth and bilateral iridocorneal angles for post-ICL follow-up assessment, providing preliminary technical validation supporting further external and device-level evaluation. Full article

Purpose: Keratoconus is a progressive corneal ectatic disorder that causes visual impairment, particularly in adolescents and young adults. Evidence on its epidemiology in Latin America and the Caribbean remains limited. This study aimed to estimate the prevalence of keratoconus and evaluate associated factors, including eye rubbing, sex, family history, and allergy history, in the region. Methods: A systematic search of PubMed, Scopus, PsycINFO, and Google Scholar was conducted on 15 December 2025 for observational studies published up to December 2025. Study selection and data extraction were performed independently by two reviewers, with disagreements resolved by consensus. Study quality was assessed using the Newcastle–Ottawa Scale. Pooled prevalence estimates and odds ratios (ORs) were calculated using a random-effects model with variance-stabilizing transformation. Heterogeneity was assessed using the I² statistic, and publication bias was explored using funnel plots and Egger’s test. Results: Seven prevalence studies were included in the primary meta-analysis following exclusion of three studies from the previous version of the review, with no additional eligible prevalence studies identified in the updated search. One additional nationwide registry-based study from Colombia was identified but excluded from the primary prevalence synthesis because it reported incidence derived from administrative diagnostic coding rather than clinically assessed prevalence. Among the seven prevalence studies, reported prevalence ranged from 0.50% to 2.88%. The pooled prevalence of keratoconus was 2.07% (95% CI: 1.53–2.79), with substantial heterogeneity (I² = 71.9%). Subgroup analyses suggested that prevalence estimates varied by study design, with lower estimates observed in community- and school-based studies and higher estimates in clinic-based studies. No statistically significant associations were identified for eye rubbing, sex, family history, or allergy history; however, these analyses should be interpreted cautiously due to small sample sizes, heterogeneous exposure definitions, and wide confidence intervals. Conclusions: Keratoconus prevalence estimates in Latin America and the Caribbean remain variable and should be interpreted cautiously due to substantial heterogeneity, differences in study design, variability in diagnostic criteria, and differences in case ascertainment. The findings highlight important evidence gaps and support the need for well-designed population-based studies using standardized diagnostic criteria to inform screening strategies, early detection, and eye-care planning in the region. Full article

Early detection of autism spectrum disorder (ASD) in young children is essential for timely referral, developmental monitoring, and access to early intervention. However, conventional screening and diagnostic pathways often depend on parent-report instruments, episodic clinical observation, and specialist-administered assessments, which may delay identification during the first years of life. This scoping review maps the methodological landscape of early ASD detection from traditional clinical screening to multimodal artificial intelligence (AI). A structured literature search was conducted across major biomedical, psychological, and engineering databases for studies published between January 2010 and May 2026. After screening and eligibility assessment, 65 evidence sources were included in the qualitative synthesis, with additional methodological guidelines used to support reporting and appraisal. The reviewed evidence shows that early ASD detection is increasingly shifting from single-session clinical assessment toward multidimensional risk characterization. Clinical and behavioral screening tools remain the foundation of early identification, while eye tracking, video-based motor analysis, acoustic and vocal biomarkers, electroencephalography (EEG), functional near-infrared spectroscopy (fNIRS), and molecular or genomic indicators provide complementary information across different developmental windows. AI-based methods, including machine learning, deep learning, Transformer architectures, multimodal fusion strategies, and foundation-model-based representation learning, may improve the objective quantification of gaze, movement, vocalization, neural activity, and biological risk. Nevertheless, most AI-assisted systems remain limited by small and heterogeneous datasets, insufficient external validation, population bias, privacy concerns, computational burden, and limited interpretability. This review argues that future early ASD detection systems should be developed as clinician-supervised decision-support tools rather than autonomous diagnostic instruments. Clinically meaningful progress will require robust external validation, privacy-preserving deployment, age-appropriate risk stratification, and intrinsically interpretable architectures that align model outputs with developmental and clinical knowledge. Full article

Background: Acute angle-closure glaucoma (AACG) is an emergency requiring rapid intervention to prevent irreversible optic nerve damage and permanent vision loss. Methods: This narrative review synthesizes the systemic medication classes most implicated in medication-induced AACG, outlining their underlying pathophysiological mechanisms, typical timing of onset, and practical risk-reduction strategies. Evidence was collected through targeted searches of the PubMed, Google Scholar, Cochrane Library, and Web of Science databases, focusing on major review articles, pharmacoepidemiologic studies, and clinical consensus guidelines. Source selection and data synthesis followed a narrative approach without formal risk of bias assessment or meta-analysis. Results: The literature consistently implicates sulfonamide derivatives (mainly topiramate), serotonergic antidepressants and triptans, potent systemic anticholinergics, and adrenergic decongestants. Sulfonamides typically precipitate bilateral, non-pupillary-block AACG via ciliochoroidal effusion, secondary anterior displacement of the lens-iris diaphragm, and an acute myopic shift. Conversely, serotonergic, anticholinergic, and adrenergic agents typically trigger classic pupillary-block AACG in anatomically predisposed eyes with pre-existing narrow angles. Adverse events predominantly occur shortly after treatment initiation or dose escalation. Management relies on prompt medication discontinuation and rapid intraocular pressure reduction. Importantly, cycloplegics are preferred over miotics in effusion-induced cases. Given the rarity of these events, brief patient education represents a pragmatic and scalable approach, although its direct clinical effectiveness in reducing event rates has not yet been formally established. Conclusions: A select group of widely prescribed systemic medications are associated with most cases of medication-induced AACG. Improving clinician awareness, providing brief patient counseling on warning symptoms, and ensuring prompt ophthalmic evaluation represent the most practical currently available risk-reduction strategies to prevent vision loss. Full article

Objectives: The VISUMAX 800 (Carl Zeiss Meditec) is the second-generation femtosecond laser for small incision lenticule extraction (SMILE), featuring faster pulse rates, automated cyclotorsion compensation (OcuLign), and automated centration (CentraLign) versus the VISUMAX 500. This systematic review and meta-analysis compared their clinical outcomes in myopia correction. Methods: Following PRISMA 2020 guidelines, we searched PubMed, EMBASE, and Web of Science through March 2026 for studies comparing the two platforms in myopia or myopic astigmatism with extractable data. Primary outcomes were predictability (SE ± 0.50 D) and astigmatism (CYL ≤ 0.50 D). Secondary outcomes included UDVA ≥ 20/20, safety (CDVA loss ≥ 1 line), R² values, surgically induced astigmatism, axis alignment (±5°), and higher-order aberrations. Risk of bias was assessed using the ROBINS-I tool for all included studies, as no randomized controlled trials were available. Publication bias was evaluated via funnel plots, Egger’s test, and Begg’s test, with appropriate caution noted regarding the limited number of studies. Sensitivity analysis used the leave-one-out method. Results: Nine studies (1672 eyes: 646 VISUMAX 800, 1026 VISUMAX 500) were included. For SE ± 0.50 D, the pooled risk ratio (RR) was 1.065 (95% CI: 0.997–1.137, p = 0.061) with substantial heterogeneity (I² = 64.7%, p = 0.004). For CYL ± 0.50 D (eight studies, 1585 eyes), the pooled RR was 1.022 (95% CI: 0.978–1.068, p = 0.333, I² = 51.7%). Astigmatism axis within ±5° significantly favored VISUMAX 800 (RR = 1.157, 95% CI: 1.071–1.250, p = 0.0002, I² = 0%). No statistically significant differences were observed for UDVA ≥ 20/20, safety, SEQ R², cylinder R², TIA, SIA, total HOAs, spherical aberration, or coma RMS. Publication bias tests showed no significant asymmetry for the primary outcomes, though these tests have limited power with fewer than 10 studies. ROBINS-I assessments classified most studies as having “serious” risk of bias due to their non-randomized designs. Conclusions: Both platforms yield comparable predictability, safety, and visual outcomes. VISUMAX 800 offers superior astigmatism axis alignment, likely due to automated compensation and centration. The borderline SE predictability warrants further randomized investigation Full article

Counterfactual thoughts about “what might have been” typically evoke emotions such as regret and relief, yet little is known about how such emotions are processed during real-time language comprehension. This eye-tracking study examined how native Chinese readers infer counterfactual emotions in narratives and whether pragmatic competence modulates this process. Participants read stories in which a character made a decision and subsequently experienced a positive or negative outcome; the final sentence was either consistent or inconsistent with the character’s feeling of regret or relief. Emotion words that mismatched the counterfactual context elicited longer reading times than matching words, indicating rapid online inference and monitoring of the protagonist’s emotions. Crucially, this emotional-consistency effect emerged earlier for relief than for regret (in first-pass reading times for relief but only in later eye-movement measures for regret), revealing an early processing advantage for relief. Moreover, individual differences in pragmatic competence selectively modulated inconsistency detection for regret but not relief: higher pragmatic competence was associated with greater early sensitivity to regret-related mismatches. These findings suggest that inferring regret places greater demands on higher-order pragmatic processing than relief and point to an optimism bias in counterfactual thinking among Chinese readers. Full article

Pedestrian detection is a fundamental component of Advanced Driver Assistance Systems (ADAS) and plays a key role in collision avoidance and the safety of vulnerable road users. This paper presents a structured review of pedestrian detection methodologies developed between 2000 and 2025, spanning classical vision techniques and modern deep learning architectures. We organize the review into two phases. First, we examine classical methods, including Histogram of Oriented Gradients (HOG)+Support Vector Machine (SVM), Viola–Jones, Deformable Part Models, and Integral Channel Features, which established the conceptual foundations of the field. Then, we analyze state-of-the-art deep learning architectures, categorized by detector stage (one-stage vs. two-stage), localization strategy (anchor-based vs. anchor-free), feature extraction paradigm (Convolutional Neural Network (CNN)-based vs. transformer-based), output representation (bounding box vs. instance segmentation), and computational profile (lightweight vs. heavyweight). Several design principles introduced by classical methods remain visible in modern architectures, indicating that they were not fully superseded. The review also examines publicly available benchmark datasets and compares the strengths and limitations of camera-, Light Detection And Ranging (LiDAR)-, radar-, and multi-sensor-fusion-based systems for ADAS deployment. We close by identifying six open problems for the field: adversarial robustness, real-time inference under embedded constraints, detection under adverse weather, dataset bias and demographic fairness, the deployment of Bird’s-Eye View (BEV) and unified perception on automotive hardware, and explainability for safety-critical use. Full article

Polysomnography (PSG) is the gold standard for diagnosing sleep disorders, but its complexity and cost limit widespread use. Heart rate variability (HRV) is traditionally assessed from electrocardiography (ECG), while photoplethysmography (PPG), widely available in wearable devices, offers a more accessible alternative. However, its reliability over full-night recordings remains underexplored. This study analyzes data from 50 subjects across five groups (healthy controls, rapid eye movement sleep behavior disorder, obstructive sleep apnea, periodic limb movements, and mixed comorbidities) to assess agreement between ECG-derived HRV and PPG-derived pulse rate variability (PRV), considering time-, frequency-, and nonlinear-domain features. Correlation and equivalence analyses were performed, with and without removal of artifactual segments. Correlation coefficients exceeded 0.6 for most features and improved to above 0.7 after artifact removal. Consistent improvements were observed across all subject groups. Equivalence testing further identified a subset of features showing high agreement and low bias. The results indicate that, with appropriate pre-processing, PPG can approximate ECG-derived variability in full-night sleep recordings. The identification of robust features for screening purposes supports the use of PRV for wearable-based screening and monitoring in heterogeneous sleep disorder populations. Full article

Background/Objectives: Borderline personality disorder (BPD) is a severe mental disorder characterised by emotion dysregulation, impulsivity and interpersonal hypersensitivity. Its prevalence ranges from 0.5% to 6.4%. Eye tracking and pupillometry provide objective indices of social attention and inhibitory control, but the BPD literature using these techniques has not been systematically reviewed. The aim of this work was to synthesise the empirical evidence on visuo-attentional and pupillary alterations in BPD. Methods: Following the PRISMA 2020 statement, Web of Science, Scopus and PubMed were searched up to 13 March 2026, with no date or language restrictions. Search terms combined borderline personality disorder and eye-tracking constructs. Two reviewers independently screened records with complete inter-rater agreement at the title-and-abstract stage (Cohen’s κ = 1.00); two generative artificial-intelligence assistants (ChatGPT, NotebookLM) were additionally consulted as a non-systematic plausibility check and returned no eligible studies beyond the database search. Risk of bias was appraised with the framework appropriate to each study design (RoB 2 for randomised trials and Newcastle–Ottawa Scale logic for observational studies, with ROBINS-I held in reserve for non-randomised intervention designs). Results: Seventeen studies met the inclusion criteria, with sample sizes ranging from 19 to 164 participants and predominantly adult female samples. Designs included antisaccade and oculomotor tasks, free-viewing, dot-probe, affective priming and pharmacological challenge. Four findings recurred across studies. First, patients with BPD showed an early reflexive vigilance to the eye region of emotional and neutral faces, followed by reduced time on positive stimuli during longer presentations. Second, self-reported impulsivity was elevated, but laboratory inhibition was largely preserved; the deficits that did emerge were limited to preparatory control and were greater in patients with comorbid ADHD or under induced negative affect. Third, autonomic dysregulation was indexed by lower heart-rate variability and a larger baseline pupil size; in a single longitudinal study, pupillary reactivity was prospectively associated with subsequent symptom change. Finally, intranasal oxytocin reduced amygdala-driven vigilance. Conclusions: Eye-tracking and pupillometric measures appear to capture meaningful aspects of the BPD clinical picture. The two-stage profile of early vigilance followed by reduced sustained engagement is most parsimoniously described as a vigilance–avoidance pattern, which is compatible with, but not uniquely explained by, the hypersensitivity hypothesis of emotion dysregulation. Because thirteen of the seventeen studies recruited women only, these conclusions apply primarily to adult women with BPD. Methodological heterogeneity, the predominance of female samples and the scarcity of longitudinal data justify the need for standardised protocols, transdiagnostic comparisons and the inclusion of male and gender-diverse populations in future research. Full article

Background: Insomnia and stress-related sleep disorders are increasingly recognized as systemic conditions linked to the microbiota–gut–brain axis (MGBA). With growing clinical interest in natural products that modulate the gut environment, this systematic review evaluates the efficacy and mechanisms of non-pharmacological interventions, specifically probiotics, prebiotics, dietary indices, and botanicals, in alleviating insomnia, restoring circadian rhythms, and modulating neurochemical markers. Methods: In strict accordance with PRISMA 2020 guidelines, we searched PubMed, ScienceDirect, Scopus, and The Cochrane Library for English language studies published from inception to March 31, 2026. Eligibility was restricted to studies with rigorously controlled designs, specifically randomized controlled trials (RCTs) and controlled in vivo animal studies. Interventions had to target the gut microbiota, with primary outcomes measuring sleep quality (subjective or objective) or sleep-related neurochemical markers. We excluded uncontrolled, single-arm, or observational designs; in vitro studies; non-original research; and studies involving subjects with severe medical or psychiatric comorbidities (e.g., cancer, ADHD, severe psychiatric disorders) to prevent confounding variables, though mild-to-moderate anxiety and depression were permitted. Risk of bias was assessed using the Cochrane RoB 2.0 and SYRCLE tools. Due to significant methodological heterogeneity, a narrative synthesis stratified by intervention and population was conducted. This review was not registered in PROSPERO. Results: A total of 56 studies (33 humans, 23 animals) met the inclusion criteria. Taxonomic nomenclature was updated to reflect 2020 reclassifications (e.g., Lactiplantibacillus plantarum). In human trials, interventions significantly improved subjective sleep metrics (PSQI, ISI). Recent additions demonstrated the efficacy of the Dietary Index for Gut Microbiota (DI-GM) and the improvement in N3 sleep latency by yeast mannan. Furthermore, whole-food patterns (e.g., the MIND diet) and Traditional Chinese Medicine (TCM) decoctions successfully enriched beneficial taxa, such as Bacteroides coprophilus, and increased short-chain fatty acid (SCFA) production. Animal models demonstrated that “psychobiotic” strains (Bifidobacterium breve, Lacticaseibacillus paracasei), prebiotics (GOS/PDX), and TCM formulas effectively restored GABA/5-HT profiles, lowered morning cortisol, and facilitated REM rebound in PCPA-induced models, while also consolidating non-rapid eye movement (NREM) sleep and downregulating clock genes (Per1/Per2). Conclusions: Psychobiotics, prebiotics, and botanicals represent a highly viable non-pharmacological strategy for treating insomnia. However, current evidence is constrained by a heavy reliance on subjective human questionnaires, short follow-up durations limiting insight into long-term stability, and a substantial translational gap between mechanistic rodent models and human clinical outcomes. Full article

LiDAR-based place recognition is critical for long-term autonomous navigation in Global Navigation Satellite System (GNSS)-denied environments, yet existing methods struggle to balance accuracy and efficiency under substantial yaw rotations. This paper proposes a robust framework based on a multi-channel polar bird’s-eye-view (BEV) representation. Under yaw-dominated revisits, the polar BEV image transforms yaw rotation into cyclic column shifts, providing a useful structural prior for rotation-equivariant feature extraction. Raw point clouds are projected onto polar BEV grids encoding density, height, and intensity. A rotation-equivariant feature extractor comprising a Radial Compression Module and a rotation-equivariant Transformer module captures long-range azimuthal dependencies via Conditional Positional Encoding and Circular Relative-Position Bias. The equivariant features are aggregated by NetVLAD into a compact global descriptor, trained end-to-end with a hard-example mining triplet loss. Extensive experiments on the public KITTI and NCLT datasets, as well as our self-constructed LiDAR Place Recognition Revisit (LPRR) dataset, demonstrate competitive performance on KITTI and superior performance on NCLT and LPRR among the compared methods. The proposed framework achieves a favorable trade-off between performance and computational cost, and shows promising cross-dataset generalization on the evaluated NCLT and LPRR datasets without fine-tuning. Full article

Background: The conventional Hess–Lancaster test is widely used to assess ocular misalignment across diagnostic gaze positions, but it relies on subjective responses and manual recording. Virtual reality may provide a more standardized framework for ocular motility assessment. Objectives: To evaluate the agreement and within-method repeatability of point-by-point deviation measurements obtained with the conventional Hess–Lancaster test and a VR-based Hess–Lancaster assessment implemented in Dicopt Pro. Methods: This cross-sectional observational study included 52 adults with suspected or diagnosed ocular motility disorders. Participants underwent both assessments using the same predefined gaze positions. Agreement was assessed using Bland–Altman analysis, concordance correlation coefficients, mean absolute differences, and mixed-effects modeling. Repeatability was evaluated in a subset with repeated measurements using session-to-session differences and intraclass correlation coefficients. Results: The VR-based assessment showed moderate agreement with the conventional test, with a mean concordance correlation coefficient of 0.57 for both eyes. Mean bias was 1.22 prism diopters for the right eye and 0.10 prism diopters for the left eye. Repeatability estimates were moderate-to-good, with ICC values ranging from 0.62 to 0.83, although repeated measurements were available only in a subset of participants. Conclusions: The VR-based Hess–Lancaster assessment showed small mean differences and moderate agreement with the conventional test, although both methods should be interpreted within the context of the complete clinical examination. Full article

In edge deployment scenarios, low-light image enhancement faces a trade-off between model complexity and perceptual quality, limiting lightweight models under resource constraints. To address this problem, this paper proposes a perceptual quality optimization model inspired by biological visual mechanisms. Specifically, a GT-Mean loss is introduced to simulate the luminance adaptation property of the mammalian retina, effectively mitigating optimization bias caused by exposure inconsistency in imaging sensors, while the LPIPS loss, aligned with the perceptual preferences of the human visual system (HVS), is incorporated to enhance subjective visual quality. From a structural perspective, inspired by the multi-scale perception of insect compound eyes, biologically selective attention, and color constancy mechanisms, the proposed model integrates an efficient texture-aware attention module, an enhanced multi-scale feature fusion strategy, and a chrominance denoising module. Experimental results demonstrate that, while maintaining an extremely low parameter count of only 0.52 M, the proposed model consistently outperforms existing lightweight methods on the LOL series datasets in terms of PSNR, SSIM, and LPIPS. This work provides an efficient perceptual quality optimization solution for bioinspired visual sensing under resource-constrained conditions. Full article