( Image credit: Densely Connected Pyramid Dehazing Network )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
In this paper, we propose a novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples, respectively.
Recently, there has been rapid and significant progress on image dehazing.
However, as these techniques destroy spatial relationship with neighboring regions, performance can be deteriorated when using them to train algorithms designed for low level vision tasks (low light image enhancement, image dehazing, deblurring, etc.)
Mail privacy protection aims to prevent unauthorized access to hidden content within an envelope since normal paper envelopes are not as safe as we think.
Extensive quantitative and perceptual experiments show that our approach obtains superior performance than state-of-the-art methods on blind video temporal consistency.
Learning to dehaze single hazy images, especially using a small training dataset is quite challenging.
Ranked #1 on Image Dehazing on O-Haze
Because of this, a number of methods have been proposed to "unprocess" nonlinear images back to a raw-RGB state.
In addition, to further enhance the performance of the method for haze removal, a patch-map-based DCP has been embedded into the network, and this module has been trained with the atmospheric light generator, patch map selection module, and refined module simultaneously.
Recently, CNN based end-to-end deep learning methods achieve superiority in Image Dehazing but they tend to fail drastically in Non-homogeneous dehazing.
Ranked #1 on Nonhomogeneous Image Dehazing on NH-HAZE validation