.png){kind=icon}
.png){kind=icon}
Return
ASM-DiffConvNet: Physics-Guided Difference Convolution Network for Single-Image Restoration
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2025.3646138.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This work proposes a physics-guided unified deep learning architecture for single image restoration targeting dehazing, deraining, and low-light enhancement. The architecture first estimates the transmission map and airlight under an atmospheric scattering model, and then refines the result with a grayscale prior. A DiffConv feature extractor is proposed which combines vanilla and difference convolutions with a Laplacian branch (to capture high-frequency features). During inference, its branches are re-parameterized into a single kernel for reducing computational complexity. The grayscale prior replaces the Y channel in the YCbCr space to suppress noise and color artifacts, while a refinement stage uses Spatial Feature Transform (SFT) to inject structural features from this grayscale prior into the RGB domain. Experiments on standard benchmarks show consistent improvements in PSNR and SSIM at lower computational cost.
Keywords:
Convolution
Image restoration
Gray-scale
Atmospheric modeling
Feature extraction
Kernel
Laplace equations
Degradation
Transformers
Accuracy
Atmospheric scattering model
difference convolution
dehazing
deraining
low light enhancement
Journal
I
IF:
3.9
Papers:
596
Citations:
0