Enlightening Low-Light Images With Dynamic Guidance for Context Enrichment

Zhu, Lingyu; Yang, Wenhan; Chen, Baoliang; Lu, Fangbo; Wang, Shiqi

doi:10.1109/tcsvt.2022.3146731

Cited by 19 publications

(2 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Global and Local Information Recovery Methods: Global and local information recovery methods enhance low-light images by combining global and local information. Zhu et al [ 22 ] proposed a deep-learning method that integrates illumination map estimation and local context enhancement. By estimating the illumination map and considering local context information, their method enhances the details and contrast of low-light images.…”

Section: Related Workmentioning

confidence: 99%

Research on Unsupervised Low-Light Railway Fastener Image Enhancement Method Based on Contrastive Learning GAN

Cai,

Liu,

et al. 2024

Sensors

View full text Add to dashboard Cite

The railway fastener, as a crucial component of railway tracks, directly influences the safety and stability of a railway system. However, in practical operation, fasteners are often in low-light conditions, such as at nighttime or within tunnels, posing significant challenges to defect detection equipment and limiting its effectiveness in real-world scenarios. To address this issue, this study proposes an unsupervised low-light image enhancement algorithm, CES-GAN, which achieves the model’s generalization and adaptability under different environmental conditions. The CES-GAN network architecture adopts a U-Net model with five layers of downsampling and upsampling structures as the generator, incorporating both global and local discriminators to help the generator to preserve image details and textures during the reconstruction process, thus enhancing the realism and intricacy of the enhanced images. The combination of the feature-consistency loss, contrastive learning loss, and illumination loss functions in the generator structure, along with the discriminator loss function in the discriminator structure, collectively promotes the clarity, realism, and illumination consistency of the images, thereby improving the quality and usability of low-light images. Through the CES-GAN algorithm, this study provides reliable visual support for railway construction sites and ensures the stable operation and accurate operation of fastener identification equipment in complex environments.

show abstract

Section: Related Workmentioning

confidence: 99%

Research on Unsupervised Low-Light Railway Fastener Image Enhancement Method Based on Contrastive Learning GAN

Cai,

Liu,

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Zhang Y [12] proposes a residual network module RDB to fuse the local and global information in the process of image super-resolution, and removes the BN layer in the network to improve the performance of super-resolution network. However, there are many reasons for underwater image distortion, such as light scattering attenuation, water turbidity, etc., the enhancement effect is not satisfactory, and there are also problems that require a large number of parameters to be calculated and labor consumption is large [13][14][15].…”

Section: Introductionmentioning

confidence: 99%