arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.12463eess.IVcs.CV
收藏

基于反馈的鲁棒表示学习的单幅图像去重

Robust Representation Learning with Feedback for Single Image Deraining

Shanghai Jiao Tong University(上海交通大学);École d’Ingénieurs SJTU-ParisTech(上海交大中法巴黎高科卓越工程师学院)

Chenghao Chen, Hao Li

摘要:

一个去覆盖网络可以被解释为一个条件生成器,旨在消除图像中的雨条纹。大多数现有的图像去水印方法忽略了模型误差所造成的不确定性,降低嵌入质量。与现有的图像去水印方法直接将低质量特征嵌入模型不同,我们用潜在的高质量特征代替低质量特征。借鉴了自动控制领域的闭环反馈的精神,以获得潜在的高质量特性。提出了一种新的检错和特征补偿方法来解决模型错误。在基准数据集和特定真实数据集上的大量实验表明,该方法优于最近的最先进的方法。代码可在:\\https://github.com/LI-Hao-SJTU/DerainRLNet

英文摘要:

A deraining network can be interpreted as a conditional generator that aims at removing rain streaks from image. Most existing image deraining methods ignore model errors caused by uncertainty that reduces embedding quality. Unlike existing image deraining methods that embed low-quality features into the model directly, we replace low-quality features by latent high-quality features. The spirit of closed-loop feedback in the automatic control field is borrowed to obtain latent high-quality features. A new method for error detection and feature compensation is proposed to address model errors. Extensive experiments on benchmark datasets as well as specific real datasets demonstrate that the proposed method outperforms recent state-of-the-art methods. Code is available at: \\ https://github.com/LI-Hao-SJTU/DerainRLNet

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑