Scholarlink

<p>Underwater computer vision faces significant challenges from light scattering, absorption, and poor illumination, which severely impact underwater vision tasks. To address these issues, ViT-Clarity, an underwater image enhancement module, is introduced, which integrates vision transformers with a convolutional neural network for superior performance. For comparison, ClarityNet, a transformer-free variant of the architecture, is presented to highlight the transformer’s impact. Given the limited availability of paired underwater image datasets (clear and degraded), BlueStyleGAN is proposed as a generative model to create synthetic underwater images from clear in-air images by simulating realistic attenuation effects. BlueStyleGAN is evaluated against existing state-of-the-art synthetic dataset generators in terms of training stability and realism. Vit-ClarityNet is rigorously tested on five datasets representing diverse underwater conditions and compared with recent state-of-the-art methods as well as ClarityNet. Evaluations include qualitative and quantitative metrics such as UCIQM, UCIQE, and the deep learning-based URanker. Additionally, the impact of enhanced images on object detection and SIFT feature matching is assessed, demonstrating the practical benefits of image enhancement for underwater computer vision tasks.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A vision transformer based CNN for underwater image enhancement ViTClarityNet

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月14日

查看全文
  • Mohamed E. Fathy,
  • Samer A. Mohamed,
  • Mohammed I. Awad,
  • Hossam E. Abd El Munim

摘要

Underwater computer vision faces significant challenges from light scattering, absorption, and poor illumination, which severely impact underwater vision tasks. To address these issues, ViT-Clarity, an underwater image enhancement module, is introduced, which integrates vision transformers with a convolutional neural network for superior performance. For comparison, ClarityNet, a transformer-free variant of the architecture, is presented to highlight the transformer’s impact. Given the limited availability of paired underwater image datasets (clear and degraded), BlueStyleGAN is proposed as a generative model to create synthetic underwater images from clear in-air images by simulating realistic attenuation effects. BlueStyleGAN is evaluated against existing state-of-the-art synthetic dataset generators in terms of training stability and realism. Vit-ClarityNet is rigorously tested on five datasets representing diverse underwater conditions and compared with recent state-of-the-art methods as well as ClarityNet. Evaluations include qualitative and quantitative metrics such as UCIQM, UCIQE, and the deep learning-based URanker. Additionally, the impact of enhanced images on object detection and SIFT feature matching is assessed, demonstrating the practical benefits of image enhancement for underwater computer vision tasks.