Chinese opera is celebrated for preserving classical art. However, early filming equipment limitations have degraded videos of last-century performances by renowned artists (e.g., low frame rates and resolution), hindering archival efforts. Although space-time video super-resolution (STVSR) has advanced significantly, applying it directly to opera videos remains challenging. The scarcity of datasets impedes the recovery of high-frequency details, and existing STVSR methods lack global modeling capabilities—compromising visual quality when handling opera’s characteristic large motions. To address these challenges, we pioneer a large-scale Chinese Opera Video Clip (COVC) dataset and propose the Mamba-based multiscale fusion network for space-time Opera Video Super-Resolution (MambaOVSR). Specifically, MambaOVSR involves three novel components: the Global Fusion Module (GFM) for motion modeling through a multiscale alternating scanning mechanism, and the Multiscale Synergistic Mamba Module (MSMM) for alignment across different sequence lengths. Additionally, our MambaVR block resolves feature artifacts and positional information loss during alignment. Experimental results on the COVC dataset show that MambaOVSR significantly outperforms the SOTA STVSR method by an average of 1.86 dB in terms of PSNR.

While semi-asynchronous federated learning (SAFL) combines the efficiency of synchronous training with the flexibility of asynchronous updates, it inherently suffers from participation bias, which is further exacerbated by non-IID data distributions. More importantly, hierarchical architecture shifts participation from individual clients to client groups, thereby further intensifying this issue. Despite notable advancements in SAFL research, most existing works still focus on conventional cloud-end architectures while largely overlooking the critical impact of non-IID data on scheduling across the cloud–edge–client hierarchy. To tackle these challenges, we propose FedCure, an innovative semiasynchronous Federated learning framework that leverages Coalition construction and participation-aware scheduling to mitigate participation bias with non-IID data. Specifically, FedCure operates through three key rules: (1) a preference rule that optimizes coalition formation by maximizing collective benefits and establishing theoretically stable partitions to reduce non-IID-induced performance degradation; (2) a scheduling rule that integrates the virtual queue technique with Bayesian-estimated coalition dynamics, mitigating efficiency loss while ensuring mean rate stability; and (3) a resource allocation rule that enhances computational efficiency by optimizing client CPU frequencies based on estimated coalition dynamics while satisfying delay requirements. Comprehensive experiments on four real-world datasets demonstrate that FedCure improves accuracy by up to 5.1x compared with four state-of-the-art baselines, while significantly enhancing efficiency with the lowest coefficient of variation 0.0223 for per-round latency and maintaining long-term balance across diverse scenarios.

Low-Light Image Enhancement (LLIE) task aims at improving contrast while restoring details and textures for images captured in low-light conditions. HVI color space has made significant progress in this task by enabling precise decoupling of chrominance and luminance. However, for the interaction of chrominance and luminance branches, substantial distributional differences between the two branches prevalent in natural images limit complementary feature extraction, and luminance errors are propagated to chrominance channels through the nonlinear parameter. Furthermore, for interaction between different chrominance branches, images with large homogeneous-color regions usually exhibit weak correlation between chrominance branches due to concentrated distributions. Traditional pixel-wise losses exploit strong inter-branch correlations for co-optimization, causing gradient conflicts in weakly correlated regions. Therefore, we propose an Inter-Chrominance and Luminance Interaction (ICLR) framework including a Dual-stream Interaction Enhancement Module (DIEM) and a Covariance Correction Loss (CCL). The DIEM improves the extraction of complementary information from two dimensions, fusion and enhancement, respectively. The CCL utilizes luminance residual statistics to penalize chrominance errors and balances gradient conflicts by constraining chrominance branches covariance. Experimental results on multiple datasets show that the proposed ICLR framework outperforms state-of-the-art methods.

Accurate dynamic modeling of task correlations is crucial for enhancing collaborative efficiency and personalized performance in federated multi-task learning (FML), yet existing approaches struggle with heterogeneous environments due to static assumptions or implicit modeling. Moreover, task relationships typically remain implicit, embedded within data distributions and parameter variations, making precise modeling inherently challenging. This challenge is further intensified in Non-IID settings, where data heterogeneity impedes both the identification and accurate estimation of task relationships. To address these challenges, we propose FedSame, a similarity-aware FML framework that leverages Bayesian inference to dynamically model inter-task relationships. The key innovation of FedSame lies in its probabilistic reformulation of task relationship modeling, where an adaptive similarity matrix undergoes continuous Bayesian updates to precisely track evolving task relationships. FedSame’s technical core combines Beta distribution priors with Bayesian update rules, enabling fine-grained detection of subtle variations in task relationship variations during training, and computationally efficient dynamic updates by leveraging the conjugacy property of the Beta distribution. Extensive experiments on two real datasets and a synthetic dataset demonstrate that FedSame consistently outperforms five state-of-the-art baselines in both task relationship modeling accuracy and multi-task classification performance. Remarkably, FedSame attains 73% accuracy in multi-attribute classification on CelebA and 85% accuracy in task relationship modeling on synthetic data, all while maintaining robust performance and notable adaptability in heterogeneous federated environments.

Federated learning (FL) facilitates privacy-preserving collaborative intelligence, making it ideal for mobile edge computing (MEC)-enabled Industrial Internet of Thing (IIoT). However, the autonomy of participants leads to unstable edge associations, hampering FL deployment. Existing studies typically prioritize device incentives but overlook price competition and network congestion at the server level. To tackle these issues, we propose coMpetition sOftening and coNgestion mItigation (MONI), a communication-efficient incentive mechanism for service pricing. Specifically, MONI employs a dynamic multiteam Bertrand game model to capture boundedly rational interactions among edge servers. It leverages capacity constraints to alleviate price competition and mitigate network congestion, while preserving the uniform stability of the game. Furthermore, MONI incorporates a genetic algorithm augmented with a truncated Gaussian distribution to minimize the disconnection of roaming devices. Experiments on synthetic and real-world industrial datasets demonstrate that MONI reduces recruitment costs and network congestion, increases the number of devices by 18.37%, and boosts model performance by up to 6.39% compared to state-of-the-art benchmarks.

Underwater image enhancement (UIE) focuses on mitigating image quality degradation due to light absorption and scattering. However, most existing methods enhance images via a global and uniform manner, neglecting the inherent semantic information in different regions, which may cause the network to easily deviate from the region’s original color. Moreover, these methods typically rely on clear images to guide network convergence, a process constrained by the limited availability of real-world datasets, making it extremely challenging to train enhancement models for various degradations. To address these challenges, this paper introduces a semantic guidance and region contrastive constraints network (SRCNet). Initially, we propose a semantic-aware RWKV (Receptance Weighted Key Value) block and a semantic prompt regularization module. These components leverage intra-target semantic correlations to preserve image details and colors within a global perceptual framework, while employing focal loss to emphasize the restoration of severely degraded regions. Subsequently, we introduce a region contrastive learning method that effectively utilizes negative samples to precisely capture features sensitive to degradation factors, thereby fostering robust feature distributions. Finally, experimental results demonstrate that our method outperforms existing state-of-the-art (SOTA) approaches.

Current low-light image enhancement (LLIE) techniques truly enhance luminance but have limited exploration on another harmful factor of nighttime visibility, the glow effects with multiple shapes in the real world. The presence of glow is inevitable due to widespread artificial light sources, and direct enhancement can cause further glow diffusion. In the pursuit of Overall Nighttime Visibility Enhancement (ONVE), we propose a physical model guided framework ONVE to derive a Nighttime Imaging Model with Near-Field Light Sources (NIM-NLS), whose APSF prior generator is validated efficiently in six categories of glow shapes. Guided by this physical-world model as domain knowledge, we subsequently develop an extensible Light-aware Blind Deconvolution Network (LBDN) to face the blind decomposition challenge on direct transmission map D and light source map G based on APSF. Then, an innovative Glow-guided Retinex-based progressive Enhancement module (GRE) is introduced as a further optimization on reflection R from D to harmonize the conflict of glow removal and brightness boost. Notably, ONVE is an unsupervised framework based on a zero-shot learning strategy and uses physical domain knowledge to form the overall pipeline and network. Empirical evaluations on multiple datasets validate the remarkable efficacy of the proposed ONVE in improving nighttime visibility and performance of high-level vision tasks.

Lifelong Vehicle Re-Identification (LVReID) aims to match a target vehicle across multiple cameras, considering non-stationary and continuous data streams, which fits the needs of the practical application better than traditional vehicle re-identification. Nonetheless, this area has received relatively little attention. Recently, methods for Lifelong Person Re-Identification (LPReID) have been emerging, with replay-based methods achieving the best results by storing a small number of instances from previous tasks for retraining, thus effectively reducing catastrophic forgetting. However, these methods cannot be directly applied to LVReID because they fail to simultaneously consider the diversity and representativeness of replayed data, resulting in biases between the subset stored in the memory buffer and the original data. They randomly sample classes, which may not adequately represent the distribution of the original data. Additionally, these methods fail to consider the rich variation in instances of the same vehicle class due to factors such as vehicle orientation and lighting conditions. Therefore, preserving more informative classes and instances for replay helps maintain information from previous tasks and may mitigate the model's forgetting of old knowledge. In view of this, we propose a novel Diversity-Representativeness Dual-Stage Sampling Replay (DDSR) strategy for LVReID that constructs an effective memory buffer through two stages, i.e. , Cluster-Centric Class Selection and Diverse Instance Mining. Specifically, we first perform class-level sampling based on density in the clustered class-centered feature space and then further mine the diverse, high-quality instances within the selected classes. In addition, we introduce Maximum Mean Discrepancy loss to align the feature distribution between replay data and the new arrivals and apply L2 regularization in the parameter space to facilitate knowledge transfer, thus enhancing the model's generalization ability to new tasks. Extensive experiments demonstrate effective improvements of our method compared to current state-of-the-art lifelong ReID methods on the VeRi-776, VehicleID, and VERI-Wild datasets.

Video stabilization is a challenging task that attempts to compensate for the overall frame shake during video acquisition. Existing three-dimensional video stabilization methods aim at modeling camera perspective projection through either data-driven training or explicit motion estimation. However, the above methods are difficult to effectively solve the issue of shaky videos with abrupt object movements, resulting in local motion blur in the direction of the movement. This phenomenon is prevalent in real-world scenarios featuring foreground blind motion scenes. Unfortunately, directly combining stabilization and deblurring methods poses challenges when dealing with this situation. In the video, the intensity of motion blur undergoes continuous changes, and the direct combination method inadequately utilizes spatiotemporal information, providing insufficient clues for cross-frame compensation. To alleviate this problem, the Cross-frame-temporal Module framework is proposed to address blind motion blur induced by various conditions, which utilizes cross-frame temporal features to estimate depth maps and camera motion. In this framework, a Blur Transform Network (BTNet) is designed to adapt to spatially varying motion blur, which transforms local regions according to the impact of blur intensities to adapt to the effects of non-uniform motion blur; furthermore, our Temporal-Aware Network (TANet) further suppresses motion blur by leveraging cross-frame temporal features. In addition, the limited availability of pair-training video data containing motion blur limits the application of this approach in practice. The Cross-frame-temporal Module framework adopts an un-pretrained in-test training strategy. Extensive experimental results have demonstrated that our method outperforms state-of-the-art methods.

Paired training is a widely-used approach in low light image enhancement(LLIE). However, normal light image with pixel wise calibration cannot be obtained at night in real scene. Then training with low light images only can be a possible solution. The generalization of low-light-image-training-only methods is also an important task, since the different training data produces different LLIE performance. To solve this problem, a diffuse map which is regarded as inherent consistent texture feature, is provided in our low stream network as guidance. Then an image-to-curve transformation is adopted achieved with our up stream to produce the final result, which is consistent with low light to extreme low light condition. A set of experiments have validated the image restoration and generalization abilities of the our method.

Most existing Low-Light Image Enhancement (LLIE) methods are primarily designed to improve brightness in dark regions, which suffer from severe degradation in nighttime images. However, these methods have limited exploration in another major visibility damage, the glow effects in real night scenes. Glow effects are inevitable in the presence of artificial light sources and cause further diffused blurring when directly enhanced. To settle this issue, we innovatively consider the glow suppression task as learning physical glow generation via multiple scattering estimation according to the Atmospheric Point Spread Function (APSF). In response to the challenges posed by uneven glow intensity and varying source shapes, an APSF-based Nighttime Imaging Model with Near-field Light Sources (NIM-NLS) is specifically derived to design a scalable Light-aware Blind Deconvolution Network (LBDN). The glow-suppressed result is then brightened via a Retinex-based Enhancement Module (REM). Remarkably, the proposed glow suppression method is based on zero-shot learning and does not rely on any paired or unpaired training data. Empirical evaluations demonstrate the effectiveness of the proposed method in both glow suppression and low-light enhancement tasks.

Deep learning networks with deeper layers become a trend for their good performance but lacks the potential for real-time mobile deployment. Another challenge for paired training networks is the limited generalization capacity caused by the sample bias. To overcome these two challenges, we propose a lightweight self-supervised low-light image enhancement method, that trains with low light images only. Specifically, our method consists of a low-resolution dense CNN network stream and a full-resolution guidance stream, responsible for image-to-curve transformation with refinement and spatial guidance fusion, respectively. Then, a new self-supervised loss function is introduced to measure the restored patch-based color deviations among color channels. Experimental results show that our method gives competitive performance to the full-supervised approaches.

It is challenging to convert a hazy color image into a gray-scale image because the color contrast field of a hazy image is distorted. In this paper, a novel decolorization algorithm is proposed to transfer a hazy image into a distortionrecovered gray-scale image. To recover the color contrast field, the relationship between the restored color contrast and its distorted input is presented in CIELab color space. Based on this restoration, a nonlinear optimization problem is formulated to construct the resultant gray-scale image. A new differentiable approximation solution is introduced to solve this problem with an extension of the Huber loss function. Experimental results show that the proposed algorithm effectively preserves the global luminance consistency while represents the original color contrast in gray-scales, which is very close to the corresponding ground truth gray-scale one.

Decolorization is to convert a color image into a gray scale image while preserve image features like salient structure and chrominance contrast. The sign of the color contrast is crucial for the decolorization algorithm and is usually determined in existing works by giving a strict defined color order or twomode weak order. In this paper, a fast computation on color order is achieved via a simple global mapping which is introduced in a linear parametric model using an extended structure transfer filter. The values of the parameters are obtained via an elegant approximation method. A local decolorization algorithm is finally designed on basis of the global linear mapping so that both color and spatial information are preserved robustly and accurately. Experimental results show that the proposed decolorization algorithms obtain a good performance among existing quality metrics for the decolorization. In addition, the proposed global decolorization algorithm is friendly to mobile devices with limited computational resource.