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.
Image Super-Resolution Using Very Deep Residual Channel Attention Networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Convolutional neural network (CNN) depth is of crucial importance for image super-resolution (SR). However, we observe that deeper networks for image SR are more difficult to train. The low-resolution inputs and features contain abundant low-frequency information, which is treated equally across channels, hence hindering the representational ability of CNNs. To solve these problems, we propose the very deep residual channel attention networks (RCAN). Specifically, we propose a residual in residual (RIR) structure to form very deep network, which consists of several residual groups with long skip connections. Each residual group contains some residual blocks with short skip connections. Meanwhile, RIR allows abundant low-frequency information to be bypassed through multiple skip connections, making the main network focus on learning high-frequency information. Furthermore, we propose a channel attention mechanism to adaptively rescale channel-wise features by considering interdependencies among channels. Extensive experiments show that our RCAN achieves better accuracy and visual improvements against state-of-the-art methods.
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
DRN uses residual distilling blocks (RDB) and groups (RDG) to achieve a better performance to model size trade-off in single image super-resolution than existing methods.
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.
-
Distilling with Residual Network for Single Image Super Resolution
DRN uses residual distilling blocks (RDB) and groups (RDG) to achieve a better performance to model size trade-off in single image super-resolution than existing methods.