arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.13281cs.CV
收藏

ECAFormer:使用交叉注意力的低光照图像增强

ECAFormer: Low-light Image Enhancement using Cross Attention

School of Mathematics and Statistics, Chongqing Jiaotong University(重庆交通大学数学与统计学院);School of Artificial Intelligence, Anhui University(安徽大学人工智能学院);College of Information Science and Technology & Artificial Intelligence, Nanjing Forestry University(南京林业大学信息科学技术与人工智能学院)

Yudi Ruan, Hao Ma, Weikai Li, Xiao Wang

AI总结:

针对低光照图像增强中模块间互补信息丢失问题,提出ECAFormer模型,通过交叉注意力与双多头自注意力实现多特征并发交互与跨层信息整合,在多个基准上PSNR提升近3%。

摘要:

低光照图像增强(LLIE)在计算机视觉中至关重要。现有的LLIE方法通常无法发现不同子组件之间的潜在关系,导致多个模块和网络层之间互补信息的丢失,最终造成图像细节的丢失。为了克服这一缺陷,我们设计了一种通过交叉注意力Transformer(ECAFormer)实现的分层相互增强,引入了一种允许多个特征并发传播和交互的架构。该模型通过引入双多头自注意力(DMSA)来保留详细信息,利用跨不同尺度的视觉和语义特征,允许它们相互引导和补充。此外,引入了跨尺度DMSA块来捕获残差连接,整合跨层信息以进一步增强图像细节。实验结果表明,ECAFormer在多个基准上达到了有竞争力的性能,PSNR比次优方法提高了近3%,证明了信息交互在LLIE中的有效性。

英文摘要:

Low-light image enhancement (LLIE) is critical in computer vision. Existing LLIE methods often fail to discover the underlying relationships between different sub-components, causing the loss of complementary information between multiple modules and network layers, ultimately resulting in the loss of image details. To beat this shortage, we design a hierarchical mutual Enhancement via a Cross Attention transformer (ECAFormer), which introduces an architecture that enables concurrent propagation and interaction of multiple features. The model preserves detailed information by introducing a Dual Multi-head self-attention (DMSA), which leverages visual and semantic features across different scales, allowing them to guide and complement each other. Besides, a Cross-Scale DMSA block is introduced to capture the residual connection, integrating cross-layer information to further enhance image detail. Experimental results show that ECAFormer reaches competitive performance across multiple benchmarks, yielding nearly a 3% improvement in PSNR over the suboptimal method, demonstrating the effectiveness of information interaction in LLIE.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑