CascadedGaze: Efficiency in Global Context Extraction for Image Restoration

arXiv:2401.15235v2 Announce Type: replace-cross
Abstract: Image restoration tasks traditionally rely on convolutional neural networks. However, given the local nature of the convolutional operator, they struggle to capture global information. The promise of attention mechanisms in Transformers is to circumvent this problem, but it comes at the cost of intensive computational overhead. Many recent studies in image restoration have focused on solving the challenge of balancing performance and computational cost via Transformer variants. In this paper, we present CascadedGaze Network (CGNet), …

abstract arxiv attention attention mechanisms computational context convolutional convolutional neural networks cost cs.cv cs.lg eess.iv efficiency extraction global however image image restoration information nature networks neural networks restoration struggle tasks transformers type