Single Image Deraining via Scale-space Invariant Attention Neural Network
원문 초록
Image enhancement from degradation of rainy artifacts plays a critical role in outdoor visual computing systems. In this paper, we tackle the notion of scale that deals with visual changes in appearance of rain steaks with respect to the camera. Specifically, we revisit multi-scale representation by scale-space theory, and propose to represent the multi-scale correlation in convolutional feature domain, which is more compact and robust than that in pixel domain. Moreover, to improve the modeling ability of the network, we do not treat the extracted multi-scale features equally, but design a novel scale-space invariant attention mechanism to help the network focus on parts of the features. In this way, we summarize the most activated presence of feature maps as the salient features. Extensive experiments results on synthetic and real rainy scenes demonstrate the superior performance of our scheme over the state-of-the-arts.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Adaptive Frequency Enhancement Network for Single Image Deraining
Degradation-Aware Feature Perturbation for All-in-One Image Restoration
Iterative Optimal Attention and Local Model for Single Image Rain Streak Removal
AllWeatherNet:Unified Image Enhancement for Autonomous Driving under Adverse Weather and Lowlight-conditions
A Hybrid Transformer-Mamba Network for Single Image Deraining
Explore Internal and External Similarity for Single Image Deraining with Graph Neural Networks
토론
이 논문과 연결된 포럼 글이 아직 없습니다.