Uni-Removal: A Semi-Supervised Framework for Simultaneously Addressing Multiple Degradations in Real-World Images

by   Yongheng Zhang, et al.

Removing multiple degradations, such as haze, rain, and blur, from real-world images poses a challenging and illposed problem. Recently, unified models that can handle different degradations have been proposed and yield promising results. However, these approaches focus on synthetic images and experience a significant performance drop when applied to realworld images. In this paper, we introduce Uni-Removal, a twostage semi-supervised framework for addressing the removal of multiple degradations in real-world images using a unified model and parameters. In the knowledge transfer stage, Uni-Removal leverages a supervised multi-teacher and student architecture in the knowledge transfer stage to facilitate learning from pretrained teacher networks specialized in different degradation types. A multi-grained contrastive loss is introduced to enhance learning from feature and image spaces. In the domain adaptation stage, unsupervised fine-tuning is performed by incorporating an adversarial discriminator on real-world images. The integration of an extended multi-grained contrastive loss and generative adversarial loss enables the adaptation of the student network from synthetic to real-world domains. Extensive experiments on real-world degraded datasets demonstrate the effectiveness of our proposed method. We compare our Uni-Removal framework with state-of-the-art supervised and unsupervised methods, showcasing its promising results in real-world image dehazing, deraining, and deblurring simultaneously.


page 1

page 4

page 8

page 9

page 11

page 12


NightHazeFormer: Single Nighttime Haze Removal Using Prior Query Transformer

Nighttime image dehazing is a challenging task due to the presence of mu...

Semi-UFormer: Semi-supervised Uncertainty-aware Transformer for Image Dehazing

Image dehazing is fundamental yet not well-solved in computer vision. Mo...

Semi-DerainGAN: A New Semi-supervised Single Image Deraining Network

Removing the rain streaks from single image is still a challenging task,...

Closing the Loop: Joint Rain Generation and Removal via Disentangled Image Translation

Existing deep learning-based image deraining methods have achieved promi...

Bridging Synthetic and Real Images: a Transferable and Multiple Consistency aided Fundus Image Enhancement Framework

Deep learning based image enhancement models have largely improved the r...

Semi-MoreGAN: A New Semi-supervised Generative Adversarial Network for Mixture of Rain Removal

Rain is one of the most common weather which can completely degrade the ...

Removing Rain Streaks via Task Transfer Learning

Due to the difficulty in collecting paired real-world training data, ima...

Please sign up or login with your details

Forgot password? Click here to reset