SRGAN-CKAN integrates convolutional Kolmogorov-Arnold networks into an adversarial super-resolution pipeline, replacing linear convolutions with spline-based nonlinear patch operators to improve perceptual quality under low computational resources.
Accurate image super-resolution using very deep convolutional networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
GMFN cascades residual dense blocks with multiple feedback connections and a gated feedback module to refine low-level features using high-level context for improved SR performance.
citing papers explorer
-
SRGAN-CKAN: Expressive Super-Resolution with Nonlinear Functional Operators under Minimal Resources
SRGAN-CKAN integrates convolutional Kolmogorov-Arnold networks into an adversarial super-resolution pipeline, replacing linear convolutions with spline-based nonlinear patch operators to improve perceptual quality under low computational resources.
-
Gated Multiple Feedback Network for Image Super-Resolution
GMFN cascades residual dense blocks with multiple feedback connections and a gated feedback module to refine low-level features using high-level context for improved SR performance.