TL;DR
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.
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...
The confidence-guided hybrid network (CGHNet) is proposed, a parallel three-branch framework that jointly performs frequency-decoupled local restoration, global context modeling, and pixel-wise degradation prior estimation and its key component is a confidence-guided feature purification mechanism.
DPCA-Net establishes a superior Pareto front between restoration fidelity and efficiency by maintaining real-time inference speeds with a minimal footprint of 15.00 GFLOPs, offering a compelling practical solution for real-time all-in-one image restoration.
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.
A lightweight dual-dimension modulation aggregation network, which combines channel-wise and spatial feature interactions to achieve more accurate reconstruction, and shows that DMANet achieves competitive reconstruction performance with lower model complexity and runtime overhead.
Experimental results show that MPINet effectively removes rain streaks of varying densities while preserving fine textures, and across all evaluated datasets, MPINet outperforms MPRNet by about 6.5% in PSNR and 1.3% in SSIM on average.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
