AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
TL;DR
This work proposes CrossMamba, a hybrid Transformer–Mamba network with Laplacian pyramid decomposition with Bayesian guided color tokenization, and designs a pyramid-level reconstruction consistency loss to jointly optimize the physical consistency of high-frequency text details and low-frequency background colors.
PixRestore is presented, a VAE-free pixel-space Diffusion Transformer (DiT) for UIR, where the diffusion backbone is trained entirely from scratch, without relying on T2I pretraining.
Image deblurring is a challenging task in computer vision because it is a difficult and spatially variant problem. This work presents a Transformer-based architecture that utilizes self-attention mechanisms to capture useful long-range dependencies in an image. Unlike traditional convolutional approaches, the proposed...
The proposed cross-attention tri-stream fusion offers a practical framework for deepfake forensics under real-world degradation, achieving a three-point improvement over the ResNet18 baseline in overall accuracy.
This paper develops a Retinex-guided state space backbone that integrates illumination–reflectance priors into the network in a structured manner, enabling more reliable restoration of shadow regions, and introduces a Shadow Interaction Module within a multi-scale channel attention framework.
A dehazing framework named DKS-Net is proposed which fully utilizes the physics guiding features and extracting structural information in the spatial domain, and a Kernel Selective Feature Extraction Module (KSFE) is introduced to effectively captures structural patterns via large-kernel convolutions with dynamic selec...
Results indicate that the proposed luminance–chroma collaborative design effectively improves reconstruction fidelity and structural preservation under the evaluated low-light conditions.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.