Direction-aware Feature-level Frequency Decomposition for Single Image Deraining
원문 초록
We present a novel direction-aware feature-level frequency decomposition network for single image deraining. Compared with existing solutions, the proposed network has three compelling characteristics. First, unlike previous algorithms, we propose to perform frequency decomposition at feature-level instead of image-level, allowing both low-frequency maps containing structures and high-frequency maps containing details to be continuously refined during the training procedure. Second, we further establish communication channels between low-frequency maps and high-frequency maps to interactively capture structures from high-frequency maps and add them back to low-frequency maps and, simultaneously, extract details from low-frequency maps and send them back to high-frequency maps, thereby removing rain streaks while preserving more delicate features in the input image. Third, different from existing algorithms using convolutional filters consistent in all directions, we propose a direction-aware filter to capture the direction of rain streaks in order to more effectively and thoroughly purge the input images of rain streaks. We extensively evaluate the proposed approach in three representative datasets and experimental results corroborate our approach consistently outperforms state-of-the-art deraining algorithms.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Iterative Optimal Attention and Local Model for Single Image Rain Streak Removal
A Hybrid Transformer-Mamba Network for Single Image Deraining
Explore Internal and External Similarity for Single Image Deraining with Graph Neural Networks
Exploiting Regional Information Transformer for Single Image Deraining
Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge
Controlling Vision-Language Models for Multi-Task Image Restoration
토론
이 논문과 연결된 포럼 글이 아직 없습니다.