基于学习的图像去雾算法在合成数据上取得了很好地性能,但是由于存在域鸿沟导致基于学习的去雾模型很难处理真实的有雾图像。为了解决该问题,本文提出域自适应范式,其中包含一个图像转换模块和两个图像去雾模块。双向图像转换模块旨在弥合合成域与真实域之间的差距,使用转换前后的图像借助一致性损失来训练去雾模块。在训练...
Domain AdaptationGenerative Adversarial NetVariational AutoencoderDeep LearningMost existing image dehazing methods based learning are less able to perform well to real hazy images. An important reason is that they are trained on synthetic hazy images whose distribution is different from real hazy images...
Specifically, a novel domain adaptation framework for real-world underwater image enhancement inspired by transfer learning is presented; it transfers in-air image dehazing to real-world underwater image enhancement. The experimental results on different real-world underwater scenes indicate that the ...
Domain Adaptation for Image Dehazing [CVPR2020] Probability Weighted Compact Feature for Domain Adaptive Retrieval [CVPR2020] [code] Disparity-Aware Domain Adaptation in Stereo Image Restoration [CVPR2020] Multi-Path Learning for Object Pose Estimation Across Domains [CVPR2020] Unsupervised Domain Adaptati...
When encountering the distribution shift between the source (training) and target (test) domains, domain adaptation attempts to adjust the classifiers to be capable of dealing with different domains. Previous domain adaptation research has achieved a lot
Domain Adaptation for Image Dehazing [CVPR2020] Probability Weighted Compact Feature for Domain Adaptive Retrieval [CVPR2020] [code] Disparity-Aware Domain Adaptation in Stereo Image Restoration [CVPR2020] Multi-Path Learning for Object Pose Estimation Across Domains [CVPR2020] Unsupervised Domain Adaptati...
Mutual Learning for Domain Adaptation: Self-distillation Image Dehazing Network with Sample-cycle Deep learning-based methods have made significant achievements for image dehazing. However, most of existing dehazing networks are concentrated on training models using simulated hazy images, resulting in genera...
Domain Adaptation for Image Dehazing [CVPR2020] Probability Weighted Compact Feature for Domain Adaptive Retrieval [CVPR2020] [code] Disparity-Aware Domain Adaptation in Stereo Image Restoration [CVPR2020] Multi-Path Learning for Object Pose Estimation Across Domains [CVPR2020] Unsupervised Domain Adaptati...
Domain Adaptation for Image Dehazing [CVPR2020] Probability Weighted Compact Feature for Domain Adaptive Retrieval [CVPR2020] [code] Disparity-Aware Domain Adaptation in Stereo Image Restoration [CVPR2020] Multi-Path Learning for Object Pose Estimation Across Domains [CVPR2020] Unsupervised Domain Adaptati...
In Domain Adaptation for Visual Understanding; Springer: Berlin/Heidelberg, Germany, 2020; pp. 33–49. [Google Scholar] Ma, J.; Xu, H.; Jiang, J.; Mei, X.; Zhang, X.P. DDcGAN: A dual-discriminator conditional generative adversarial network for multi-resolution image fusion. IEEE Trans...