Saved in:
Bibliographic Details
Main Authors: Ruan, Yudi, Ma, Hao, Li, Weikai, Wang, Xiao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.13281
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915074618163200
author Ruan, Yudi
Ma, Hao
Li, Weikai
Wang, Xiao
author_facet Ruan, Yudi
Ma, Hao
Li, Weikai
Wang, Xiao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_13281
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ECAFormer: Low-light Image Enhancement using Cross Attention
Ruan, Yudi
Ma, Hao
Li, Weikai
Wang, Xiao
Computer Vision and Pattern Recognition
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.
title ECAFormer: Low-light Image Enhancement using Cross Attention
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.13281