UCL-Dehaze: Towards Real-world Image Dehazing via Unsupervised Contrastive Learning

05/04/2022
by   Yongzhen Wang, et al.
0

While the wisdom of training an image dehazing model on synthetic hazy data can alleviate the difficulty of collecting real-world hazy/clean image pairs, it brings the well-known domain shift problem. From a different yet new perspective, this paper explores contrastive learning with an adversarial training effort to leverage unpaired real-world hazy and clean images, thus bridging the gap between synthetic and real-world haze is avoided. We propose an effective unsupervised contrastive learning paradigm for image dehazing, dubbed UCL-Dehaze. Unpaired real-world clean and hazy images are easily captured, and will serve as the important positive and negative samples respectively when training our UCL-Dehaze network. To train the network more effectively, we formulate a new self-contrastive perceptual loss function, which encourages the restored images to approach the positive samples and keep away from the negative samples in the embedding space. Besides the overall network architecture of UCL-Dehaze, adversarial training is utilized to align the distributions between the positive samples and the dehazed images. Compared with recent image dehazing works, UCL-Dehaze does not require paired data during training and utilizes unpaired positive/negative data to better enhance the dehazing performance. We conduct comprehensive experiments to evaluate our UCL-Dehaze and demonstrate its superiority over the state-of-the-arts, even only 1,800 unpaired real-world images are used to train our network. Source code has been available at https://github.com/yz-wang/UCL-Dehaze.

READ FULL TEXT

page 2

page 4

page 8

page 9

page 11

page 12

research
10/23/2022

Rethinking Rotation in Self-Supervised Contrastive Learning: Adaptive Positive or Negative Data Augmentation

Rotation is frequently listed as a candidate for data augmentation in co...
research
01/23/2023

RainDiffusion:When Unsupervised Learning Meets Diffusion Models for Real-world Image Deraining

What will happen when unsupervised learning meets diffusion models for r...
research
03/22/2022

Unsupervised Deraining: Where Contrastive Learning Meets Self-similarity

Image deraining is a typical low-level image restoration task, which aim...
research
06/30/2020

SCE: Scalable Network Embedding from Sparsest Cut

Large-scale network embedding is to learn a latent representation for ea...
research
07/14/2020

UDBNET: Unsupervised Document Binarization Network via Adversarial Game

Degraded document image binarization is one of the most challenging task...
research
04/25/2023

Unsupervised Synthetic Image Refinement via Contrastive Learning and Consistent Semantic-Structural Constraints

Ensuring the realism of computer-generated synthetic images is crucial t...
research
03/27/2022

CaCo: Both Positive and Negative Samples are Directly Learnable via Cooperative-adversarial Contrastive Learning

As a representative self-supervised method, contrastive learning has ach...

Please sign up or login with your details

Forgot password? Click here to reset