Curricular Contrastive Regularization for Physics-aware Single Image Dehazing

by   Yu Zheng, et al.

Considering the ill-posed nature, contrastive regularization has been developed for single image dehazing, introducing the information from negative images as a lower bound. However, the contrastive samples are nonconsensual, as the negatives are usually represented distantly from the clear (i.e., positive) image, leaving the solution space still under-constricted. Moreover, the interpretability of deep dehazing models is underexplored towards the physics of the hazing process. In this paper, we propose a novel curricular contrastive regularization targeted at a consensual contrastive space as opposed to a non-consensual one. Our negatives, which provide better lower-bound constraints, can be assembled from 1) the hazy image, and 2) corresponding restorations by other existing methods. Further, due to the different similarities between the embeddings of the clear image and negatives, the learning difficulty of the multiple components is intrinsically imbalanced. To tackle this issue, we customize a curriculum learning strategy to reweight the importance of different negatives. In addition, to improve the interpretability in the feature space, we build a physics-aware dual-branch unit according to the atmospheric scattering model. With the unit, as well as curricular contrastive regularization, we establish our dehazing network, named C2PNet. Extensive experiments demonstrate that our C2PNet significantly outperforms state-of-the-art methods, with extreme PSNR boosts of 3.94dB and 1.50dB, respectively, on SOTS-indoor and SOTS-outdoor datasets.


page 4

page 6

page 7


Contrastive Learning for Compact Single Image Dehazing

Single image dehazing is a challenging ill-posed problem due to the seve...

Restoring Vision in Hazy Weather with Hierarchical Contrastive Learning

Image restoration under hazy weather condition, which is called single i...

Whitening-based Contrastive Learning of Sentence Embeddings

This paper presents a whitening-based contrastive learning method for se...

Causality-based Dual-Contrastive Learning Framework for Domain Generalization

Domain Generalization (DG) is essentially a sub-branch of out-of-distrib...

Spectral normalized dual contrastive regularization for image-to-image translation

Existing image-to-image(I2I) translation methods achieve state-of-the-ar...

Contrastive Learning for Local and Global Learning MRI Reconstruction

Magnetic Resonance Imaging (MRI) is an important medical imaging modalit...

ConR: Contrastive Regularizer for Deep Imbalanced Regression

Imbalanced distributions are ubiquitous in real-world data. They create ...

Please sign up or login with your details

Forgot password? Click here to reset