paper-with-me

홈 › Papers

Non-aligned supervision for Real Image Dehazing

2023-03-08 · Junkai Fan, Fei Guo, Jianjun Qian, Xiang Li, Jun Li, Jian Yang

Removing haze from real-world images is challenging due to unpredictable weather conditions, resulting in the misalignment of hazy and clear image pairs. In this paper, we propose an innovative dehazing framework that operates under non-aligned supervision. This framework is grounded in the atmospheric scattering model, and consists of three interconnected networks: dehazing, airlight, and transmission networks. In particular, we explore a non-alignment scenario that a clear reference image, unaligned with the input hazy image, is utilized to supervise the dehazing network. To implement this, we present a multi-scale reference loss that compares the feature representations between the referred image and the dehazed output. Our scenario makes it easier to collect hazy/clear image pairs in real-world environments, even under conditions of misalignment and shift views. To showcase the effectiveness of our scenario, we have collected a new hazy dataset including 415 image pairs captured by mobile Phone in both rural and urban areas, called "Phone-Hazy". Furthermore, we introduce a self-attention network based on mean and variance for modeling real infinite airlight, using the dark channel prior as positional guidance. Additionally, a channel attention network is employed to estimate the three-channel transmission. Experimental results demonstrate the superior performance of our framework over existing state-of-the-art techniques in the real-world image dehazing task. Phone-Hazy and code will be available at https://fanjunkai1.github.io/projectpage/NSDNet/index.html.

📄 PDF Abstract BibTeX arXiv:2303.04940

Code (0)

등록된 구현이 없습니다.

Tasks

Image Dehazing

Similar Papers 제목 키워드 기반

CLIP-Guided Data Augmentation for Night-Time Image Dehazing

2026-04-07 · Xining Ge, Weijun Yuan, Gengjia Chang, Xuyang Li 외 arxiv

Nighttime image dehazing faces a more complex degradation pattern than its daytime counterpart, as haze scattering couples with low illumination, non-uniform lighting, and strong light interference. Under limited supervi…

Data AugmentationImage Dehazing

Learning To Restore Hazy Video: A New Real-World Dataset and a New Method

2021-06-19 · CVPR 2021 1 · Xinyi Zhang, Hang Dong, Jinshan Pan, Chao Zhu 외

Most of the existing deep learning-based dehazing methods are trained and evaluated on the image dehazing datasets, where the dehazed images are generated by only exploiting the information from the corresponding haz…

Image Dehazing

Efficient Unpaired Image Dehazing with Cyclic Perceptual-Depth Supervision

2020-07-10 · Chen Liu, Jiaqi Fan, Guosheng Yin

Image dehazing without paired haze-free images is of immense importance, as acquiring paired images often entails significant cost. However, we observe that previous unpaired image dehazing approaches tend to suffer from…

Image Dehazing

Driving-Video Dehazing with Non-Aligned Regularization for Safety Assistance

2024-05-16 · CVPR 2024 1 · Junkai Fan, Jiangwei Weng, Kun Wang, Yijun Yang 외

Real driving-video dehazing poses a significant challenge due to the inherent difficulty in acquiring precisely aligned hazy/clear video pairs for effective model training, especially in dynamic driving scenarios with un…

LAP-Net: Level-Aware Progressive Network for Image Dehazing

2019-10-01 · ICCV 2019 10 · Yunan Li, Qiguang Miao, Wanli Ouyang, Zhenxin Ma 외

In this paper, we propose a level-aware progressive network (LAP-Net) for single image dehazing. Unlike previous multi-stage algorithms that generally learn in a coarse-to-fine fashion, each stage of LAP-Net learns diffe…

Image DehazingSingle Image Dehazing