Similar papers
2026
Person-Prioritized Restoration for High-Compression 360° Video
High-Compression videos suffer from severe distortions, among which degradation in person regions has the greatest impact on viewers’ immersive experience. Existing quality enhancement techniques usually focus on overall image denoising or super-resolution, often overlooking the crucial recovery of fine structures in these essential person regions. To address these challenges, the research introduces a novel framework titled Person Region Restoration Driven by Perceptual Fidelity (PRRDPF), which combines long-range dependency features with perceptual structure loss for enhanced generative restoration. Specifically, first, the research constructs a high-fidelity distorted person-region dataset via a closed-loop degradation pipeline, addressing the lack of paired datasets. Secondly, a Temporal Gated Fusion (TGF) block is designed to use gated convolutions for selectively recovering high-frequency features while capturing local and global dependencies. Finally, a Structural Similarity Index Measure (SSIM)-based dynamic weighted adversarial loss is proposed to prioritize the restoration of visual texture details. Experimental results validate that PRRDPF significantly outperforms the best models in Peak Signal-to-Noise Ratio (PSNR), SSIM, and Learned Perceptual Image Patch Similarity (LPIPS), effectively mitigating artifacts and enhancing clarity in person visuals. This framework presents a promising approach for intelligent video coding integrated with generative artificial intelligence and holds significant potential for practical applications.
Linyun Liu, Li Yu, Jiaxin Zeng et al.
· IEEE Signal Processing Lette... · 0 citations
Open access
Jul 2026
Enhancing low-light images with MSHCDI-Net: A multi-scale hybrid cross-domain interaction approach
Low-light image enhancement aims to improve visual visibility and perceptual quality under challenging illumination conditions. However, conventional convolutional neural networks (CNNs) are inherently limited in modeling long-range dependencies due to their restricted receptive fields, which often leads to insufficient global context modeling and suboptimal restoration results. To address this limitation, we propose MSHCDI-Net, a Multi-Scale Hybrid Cross-Domain Interaction Network that effectively integrates CNN and Transformer branches to jointly capture local texture details and global contextual relationships. Specifically, the proposed framework adopts a hierarchical encoder–decoder architecture to perform multi-scale feature extraction and progressive reconstruction. A cross-domain interaction mechanism is introduced to facilitate effective information exchange between convolutional and Transformer representations across multiple resolutions, enabling complementary modeling of fine-grained structures and long-range dependencies. Through adaptive feature fusion and multi-scale guidance, the network achieves improved structural consistency and detail restoration in low-light scenes. Extensive experiments on several public benchmarks demonstrate the effectiveness of the proposed method. MSHCDI-Net achieves 23.45 dB PSNR / 0.848 SSIM on LOL-v1, 23.74 dB / 0.910 SSIM on LOL-v2-synthetic, and 22.24 dB / 0.868 SSIM on LOL-v2-real, demonstrating competitive performance in both quantitative metrics and visual quality.
Bin Chen, Peitao Li, Chaobing Zheng et al.
· PLoS ONE · 0 citations
Preprint
Jul 2026
Generalized Synthetic Image Detection with Enhanced RGB-Noise Representation Learning
The rapid advancement of large-scale generative models has accelerated the spread of highly deceptive AI-generated images, making generalized synthetic image detection a critical imperative. Existing forensic networks often struggle with cross-model generalization and realworld degradations due to their reliance on single-domain representations and conventional binary classification optimization. To overcome these limitations, we propose RNSIDNet, a novel forensic framework that achieves robust detection through enhanced RGB-Noise representation learning. Specifically, our method employs a dual-branch architecture where global RGB semantics, extracted by an attention-refined CLIP backbone, dynamically modulate highfrequency noise artifacts captured by Bayar convolutions via a Feature-wise Linear Modulation (FiLM) module. To further enhance the learned representations, we design a Hard Sample-aware Contrastive Learning (HSCL) strategy. By explicitly penalizing challenging training samples, HSCL reshapes the latent feature space to maximize the discriminative margin between pristine and synthetic domains. Extensive experiments across eight public benchmark datasets verify that our model achieves state-of-the-art performance, delivering superior generalization ability, robustness, and computational efficiency. Code and dataset will be publicly available on https://github.com/multimediaFor/RNSIDNet.
Zhen Li, Gang Cao, Tianyi Zhang et al.
· 0 citations
Jul 2026
Multi-condition guided diffusion model for face sketch-to-photo synthesis.
A diffusion-based framework with a stage-wise multi-condition guidance mechanism that enhances both structural and textural fidelity and compares with recent image-to-image translation and diffusion-based baselines to observe competitive performance in both visual coherence and identity preservation.
Yue Que, Xuegui Cheng, Shuqian Shi et al.
· Neural Networks · 0 citations
Open access
Aug 2026
A Novel Image Inpainting Model Based on Multi-scale Parallel Dense Connection Network
Existing image inpainting methods often fail to effectively exploit multi-scale feature information and lack sufficient interaction between shallow and deep representations, leading to unsatisfactory restoration performance in damaged regions. In addition, structural discontinuities and blurred details frequently occur near the boundaries of missing areas. To address these challenges, this paper proposes a novel image inpainting framework based on a Multi-Scale Parallel Dense Connection Network (MSPDCN). Specifically, holistically nested edge detection (HED) is first employed to extract structural priors and estimate edge information of missing regions, which provides guidance for subsequent reconstruction and alleviates boundary blurring. Subsequently, a multi-scale parallel dense connection module is integrated into the generation network to capture features with different receptive fields and to strengthen the interaction between hierarchical representations, thereby improving feature utilization. Extensive experiments are conducted to evaluate the proposed model against state-of-the-art methods, including GAN-based and diffusion-based approaches. Compared with the contextual attention (CA) model, the proposed method achieves improvements of 13.09% and 5.12% in PSNR and SSIM, respectively, while reducing LPIPS by 21.72%. The results demonstrate that the proposed MSPDCN not only enhances visual quality but also improves robustness to interference. Overall, the proposed approach consistently outperforms existing methods in image inpainting tasks.
Jie Wang, Li-Yuan Zhang, Yi-Bo Deng et al.
· 電腦學刊 · 0 citations
Jul 2026
AKNet: an aligned kernel network for image restoration
An efficient aligned kernel network (AKNet) is proposed, which innovatively employs super-large convolution kernels to capture global receptive fields with minimal computational overhead, effectively mimicking the long-range dependency modeling of transformers.
Wan Li, Xiao-Lin Zhang
· The Visual Computer · 0 citations