SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.09367 · CVPR · 2021

Contrastive Learning for Compact Single Image Dehazing

Yuan Xie, Zhizhong Zhang, Lizhuang Ma, Shaohui Lin, Ruizhi Qiao, Haiyan Wu, Yanyun Qu, Jian Zhou

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Single image dehazing is a challenging ill-posed problem due to the severe information degeneration. However, existing deep learning based dehazing methods only adopt clear images as positive samples to guide the training of dehazing network while negative information is unexploited. Moreover, most of them focus on strengthening the dehazing network with an increase of depth and width, leading to a significant requirement of computation and memory. 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. CR ensures that the restored image is pulled to closer to the clear image and pushed to far away from the hazy image in the representation space. Furthermore, considering trade-off between performance and memory storage, we develop a compact dehazing network based on autoencoder-like (AE) framework. It involves an adaptive mixup operation and a dynamic feature enhancement module, which can benefit from preserving information flow adaptively and expanding the receptive field to improve the network's transformation capability, respectively. We term our dehazing network with autoencoder and contrastive regularization as AECR-Net. The extensive experiments on synthetic and real-world datasets demonstrate that our AECR-Net surpass the state-of-the-art approaches. The code is released in https://github. com/GlassyWu/AECR-Net.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2104.09367")
get_code_for_paper("2104.09367")
have("2104.09367")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2104.09367.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2104.09367.svg)](https://syntology.ai/paper/2104.09367)

Connect an agent — have() is free.