PANet: A Physics-guided Parametric Augmentation Net for Image Dehazing by Hazing
- URL: http://arxiv.org/abs/2404.09269v1
- Date: Sun, 14 Apr 2024 14:24:13 GMT
- Title: PANet: A Physics-guided Parametric Augmentation Net for Image Dehazing by Hazing
- Authors: Chih-Ling Chang, Fu-Jen Tsai, Zi-Ling Huang, Lin Gu, Chia-Wen Lin,
- Abstract summary: A huge domain gap between synthetic and real-world haze images degrades dehazing performance in practical settings.
We propose a Physics-guided Parametric Augmentation Network (PANet) that generates photo-realistic hazy and clean training pairs.
Our experimental results demonstrate that PANet can augment diverse realistic hazy images to enrich existing hazy image benchmarks.
- Score: 33.39324790342096
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Image dehazing faces challenges when dealing with hazy images in real-world scenarios. A huge domain gap between synthetic and real-world haze images degrades dehazing performance in practical settings. However, collecting real-world image datasets for training dehazing models is challenging since both hazy and clean pairs must be captured under the same conditions. In this paper, we propose a Physics-guided Parametric Augmentation Network (PANet) that generates photo-realistic hazy and clean training pairs to effectively enhance real-world dehazing performance. PANet comprises a Haze-to-Parameter Mapper (HPM) to project hazy images into a parameter space and a Parameter-to-Haze Mapper (PHM) to map the resampled haze parameters back to hazy images. In the parameter space, we can pixel-wisely resample individual haze parameter maps to generate diverse hazy images with physically-explainable haze conditions unseen in the training set. Our experimental results demonstrate that PANet can augment diverse realistic hazy images to enrich existing hazy image benchmarks so as to effectively boost the performances of state-of-the-art image dehazing models.
Related papers
- LMHaze: Intensity-aware Image Dehazing with a Large-scale Multi-intensity Real Haze Dataset [14.141433473509826]
We present LMHaze, a large-scale, high-quality real-world dataset.
LMHaze comprises paired hazy and haze-free images captured in diverse indoor and outdoor environments.
To better handle images with different haze intensities, we propose a mixture-of-experts model based on Mamba.
arXiv Detail & Related papers (2024-10-21T15:20:02Z) - HazeSpace2M: A Dataset for Haze Aware Single Image Dehazing [26.97153700921866]
This research introduces the HazeSpace2M dataset, a collection of over 2 million images designed to enhance dehazing through haze type classification.
Using the dataset, we introduce a technique of haze type classification followed by specialized dehazers to clear hazy images.
Our approach classifies haze types before applying type-specific dehazing, improving clarity in real-life hazy images.
arXiv Detail & Related papers (2024-09-25T23:47:25Z) - HazeCLIP: Towards Language Guided Real-World Image Dehazing [62.4454483961341]
Existing methods have achieved remarkable performance in image dehazing, particularly on synthetic datasets.
This paper introduces HazeCLIP, a language-guided adaptation framework designed to enhance the real-world performance of pre-trained dehazing networks.
arXiv Detail & Related papers (2024-07-18T17:18:25Z) - SynFog: A Photo-realistic Synthetic Fog Dataset based on End-to-end Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving [48.27575423606407]
We introduce an end-to-end simulation pipeline designed to generate photo-realistic foggy images.
We present a new synthetic fog dataset named SynFog, which features both sky light and active lighting conditions.
Experimental results demonstrate that models trained on SynFog exhibit superior performance in visual perception and detection accuracy.
arXiv Detail & Related papers (2024-03-25T18:32:41Z) - SIR: Self-supervised Image Rectification via Seeing the Same Scene from
Multiple Different Lenses [82.56853587380168]
We propose a novel self-supervised image rectification (SIR) method based on an important insight that the rectified results of distorted images of the same scene from different lens should be the same.
We leverage a differentiable warping module to generate the rectified images and re-distorted images from the distortion parameters.
Our method achieves comparable or even better performance than the supervised baseline method and representative state-of-the-art methods.
arXiv Detail & Related papers (2020-11-30T08:23:25Z) - Dehaze-GLCGAN: Unpaired Single Image De-hazing via Adversarial Training [3.5788754401889014]
We propose a dehazing Global-Local Cycle-consistent Generative Adversarial Network (Dehaze-GLCGAN) for single image de-hazing.
Our experiments over three benchmark datasets show that our network outperforms previous work in terms of PSNR and SSIM.
arXiv Detail & Related papers (2020-08-15T02:43:00Z) - NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and
Haze-Free Images [95.00583228823446]
NH-HAZE is a non-homogeneous realistic dataset with pairs of real hazy and corresponding haze-free images.
This work presents an objective assessment of several state-of-the-art single image dehazing methods that were evaluated using NH-HAZE dataset.
arXiv Detail & Related papers (2020-05-07T15:50:37Z) - FD-GAN: Generative Adversarial Networks with Fusion-discriminator for
Single Image Dehazing [48.65974971543703]
We propose a fully end-to-end Generative Adversarial Networks with Fusion-discriminator (FD-GAN) for image dehazing.
Our model can generator more natural and realistic dehazed images with less color distortion and fewer artifacts.
Experiments have shown that our method reaches state-of-the-art performance on both public synthetic datasets and real-world images.
arXiv Detail & Related papers (2020-01-20T04:36:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.