Algorithm Achieves 0.905 Average Precision Identifying Cold Region Bridge Defects
An intelligent framework combining progressive image restoration and an improved YOLOv11 detector achieved an average precision of 0.905 when identifying ...
An intelligent framework combining progressive image restoration and an improved YOLOv11 detector achieved an average precision of 0.905 when identifying ...
Engineers developed PGU-Depth, a self-supervised monocular depth estimation framework that integrates physical medium transmission maps to overcome underwater optical degradation.
A physics-driven video dehazing framework models spatially varying atmospheric light and integrates depth priors to eliminate temporal flickering while significantly ...
A new deep learning framework leverages degradation-aware modules to restore ancient Chinese murals and inscriptional images with improved structural and ...
Researchers have introduced MPD-Net, a dual-candidate dehazing network that improves image clarity and maintains hue fidelity across foggy maritime port ...
A Channel Dense Dense U-Generative Adversarial Network restored image quality and quantitative uptake accuracy in four-fold accelerated PSMA PET imaging ...
Researchers report a maritime image dehazing framework combining physics-based haze synthesis, color-aware attention and progressive learning that achieved top SSIM ...
A four-channel neural network using co-acquired atomic force microscopy signals improved image restoration, outperformed larger single-channel models and reduced training-data ...
A new AI framework called GECST combines generative adversarial networks with classical compositional rules to restore China's fading Dunhuang murals ...
Researchers have built AMIFound, a single foundation model trained on 3.76 million image pairs that restores and enhances medical images ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine