Ghost-Unet: multi-stage network for image deblurring via lightweight subnet learning

Feng, Ziliang; Zhang, Ju; Ran, Xusong; Li, Donglu; Zhang, Chengfang

doi:10.1007/s00371-024-03315-4

Cited by 1 publication

(1 citation statement)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Xu et al applied internal connection aggregation units to utilize global information and aggregate features of different scales to extract more scene details; at the same time, they used external connection enhancement units to obtain effective feature maps [27]. Feng et al proposed a new multi-stage network deblurring model [28], in which lightweight subnetworks are embedded into each stage of the model to gradually learn input image features to promote process optimization. Zhang et al proposed the Residual Dense Block (RDB) [29].…”

Section: Related Workmentioning

confidence: 99%

MRD-Net: Multi-scale Refinement Dehazing Network for Autonomous Driving Perception Images

Wang,

et al. 2024

Preprint

View full text Add to dashboard Cite

In hazy weather conditions, a significant accumulation of haze poses a severe challenge to the quality of image capture for autonomous driving systems, thereby heightening safety risks for autonomous vehicles. To tackle this issue, we propose the Multi-scale Refinement Dehazing Network (MRD-Net), an innovative architecture comprising a front-end module, a backbone module, and a tail-end module, specifically designed to eradicate haze with precision. To enhance the extraction of multi-scale features, the backbone module employs the Squeeze-Excitation Residual Dense Block (SRD). It not only learns the intricate multi-scale features of the image but also adaptively recalibrates the feature response of each feature map, ultimately bolstering the network's performance and resilience. The tail-end module, crafted with the Dilation Refinement Block (DRB), serves as a compensatory measure for any detail loss or pseudo-artifacts that might arise from the backbone module's operations. By incorporating this refinement block, the overall dehazing effect is further optimized. Empirical evaluations reveal that the proposed MRD-Net achieves impressive results, with a PSNR value of 28.12, an SSIM value of 0.964, and an LPIPS value of 0.032. These figures indicate that the network is adept at removing haze from images while preserving intricate details, ensuring the efficacy and reliability of autonomous driving systems in hazy environments.

show abstract

Section: Related Workmentioning

confidence: 99%

MRD-Net: Multi-scale Refinement Dehazing Network for Autonomous Driving Perception Images

Wang,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Ghost-Unet: multi-stage network for image deblurring via lightweight subnet learning

Cited by 1 publication

References 39 publications

MRD-Net: Multi-scale Refinement Dehazing Network for Autonomous Driving Perception Images

MRD-Net: Multi-scale Refinement Dehazing Network for Autonomous Driving Perception Images

Contact Info

Product

Resources

About