paper-with-me

홈 › Papers

ECAFormer: Low-light Image Enhancement using Cross Attention

2024-06-19 · Yudi Ruan, Hao Ma, Weikai Li, Xiao Wang

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.

📄 PDF Abstract BibTeX arXiv:2406.13281

Code (1)

ruanyudi/ecaformer 공식 구현 pytorch

Tasks

Autonomous DrivingImage EnhancementLow-Light Image EnhancementSSIM

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

RT-X Net: RGB-Thermal cross attention network for Low-Light Image Enhancement

2025-05-30 · Raman Jha, Adithya Lenka, Mani Ramanagopal, Aswin Sankaranarayanan 외

In nighttime conditions, high noise levels and bright illumination sources degrade image quality, making low-light image enhancement challenging. Thermal images provide complementary information, offering richer textures…

Image EnhancementLow-Light Image Enhancement

PPformer: Using pixel-wise and patch-wise cross-attention for low-light image enhancement

2024-01-15 · Computer Vision and Image Understanding 2024 1 · J Dang, Y Zhong, X Qin

Recently, transformer-based methods have shown strong competition compared to CNN-based methods on the low-light image enhancement task, by employing the self-attention for feature extraction. Transformer-based methods p…

Image EnhancementLow-Light Image Enhancement

Bright Channel Prior Attention for Multispectral Pedestrian Detection

2023-05-22 · Chenhang Cui, Jinyu Xie, Yechenhao Yang

Multispectral methods have gained considerable attention due to their promising performance across various fields. However, most existing methods cannot effectively utilize information from two modalities while optimizin…

Image Enhancementobject-detectionObject DetectionPedestrian Detection

SDI-Net: Toward Sufficient Dual-View Interaction for Low-light Stereo Image Enhancement

2024-08-20 · Linlin Hu, Ao Sun, Shijie Hao, Richang Hong 외

Currently, most low-light image enhancement methods only consider information from a single view, neglecting the correlation between cross-view information. Therefore, the enhancement results produced by these methods ar…

DecoderImage EnhancementLow-Light Image Enhancement

Color-wise Attention Network for Low-light Image Enhancement

2020-05-16

Absence of nearby light sources while capturing an image will degrade the visibility and quality of the captured image, making computer vision tasks difficult. In this paper, a color-wise attention network (CWAN) is prop…

Image EnhancementLow-Light Image Enhancement