计算机科学
图像复原
光学(聚焦)
图像(数学)
人工智能
残余物
计算
匹配(统计)
计算复杂性理论
计算机视觉
图像编辑
模式识别(心理学)
网络体系结构
稀疏逼近
稀疏矩阵
迭代重建
运动(物理)
图像处理
计算摄影
建筑
作者
Shuting Dong,Zirong Wu,Hongyang Wei,Mingzhi Chen,Guanghao Li,He Qian,Hanyang Peng,Chun Lan Yuan
标识
DOI:10.1109/tmm.2025.3618558
摘要
Image restoration aims to restore high-quality images from degraded inputs caused by factors such as motion blur, defocus blur, and rain, where the primary difference between degraded and high-quality images lies in their high-frequency components. Despite the critical role of high frequencies in restoration, few methods explicitly prioritize computational resources for high frequencies over low frequencies. To address this issue, we propose a High-Frequency Prioritized Sparse Attention Network (HFP-SAN), a novel architecture for image restoration tasks. We explicitly prioritize high-frequency components by designing a symmetric encoder-decoder framework integrated with High-Frequency Selective Sparse Attention (HFSSA) modules while handling low-frequency components with a smaller residual network, thereby proportionally allocating computational resources based on their relative importance. HFSSA incorporates a Frequency-Selective Matching (FSM) algorithm to focus attention on strongly correlated high-frequency regions, mitigating computation on areas with weak correlations and irrelevant areas. Additionally, we introduce a dynamically adjustable high-frequency mask that guides the network to focus on the severely degraded regions, further refining restoration quality. The above designs ensure the final reconstructed image is a high-quality product. Experiments demonstrate that our HFP-SAN achieves state-of-the-art performance across multiple image restoration tasks, both quantitatively and qualitatively.
科研通智能强力驱动
Strongly Powered by AbleSci AI