Unsupervised Neural Rendering for Image Hazing

• URL: http://arxiv.org/abs/2107.06681v1
• Date: Wed, 14 Jul 2021 13:15:14 GMT
• Title: Unsupervised Neural Rendering for Image Hazing
• Authors: Boyun Li, Yijie Lin, Xiao Liu, Peng Hu, Jiancheng Lv and Xi Peng
• Abstract summary: Image hazing aims to render a hazy image from a given clean one, which could be applied to a variety of practical applications such as gaming, filming, photographic filtering, and image dehazing. We propose a neural rendering method for image hazing, dubbed as HazeGEN. To be specific, HazeGEN is a knowledge-driven neural network which estimates the transmission map by leveraging a new prior. To adaptively learn the airlight, we build a neural module based on another new prior, i.e., the rendered hazy image and the exemplar are similar in the airlight distribution.
• Score: 31.108654945661705
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image hazing aims to render a hazy image from a given clean one, which could be applied to a variety of practical applications such as gaming, filming, photographic filtering, and image dehazing. To generate plausible haze, we study two less-touched but challenging problems in hazy image rendering, namely, i) how to estimate the transmission map from a single image without auxiliary information, and ii) how to adaptively learn the airlight from exemplars, i.e., unpaired real hazy images. To this end, we propose a neural rendering method for image hazing, dubbed as HazeGEN. To be specific, HazeGEN is a knowledge-driven neural network which estimates the transmission map by leveraging a new prior, i.e., there exists the structure similarity (e.g., contour and luminance) between the transmission map and the input clean image. To adaptively learn the airlight, we build a neural module based on another new prior, i.e., the rendered hazy image and the exemplar are similar in the airlight distribution. To the best of our knowledge, this could be the first attempt to deeply rendering hazy images in an unsupervised fashion. Comparing with existing haze generation methods, HazeGEN renders the hazy images in an unsupervised, learnable, and controllable manner, thus avoiding the labor-intensive efforts in paired data collection and the domain-shift issue in haze generation. Extensive experiments show the promising performance of our method comparing with some baselines in both qualitative and quantitative comparisons. The code will be released on GitHub after acceptance.

Related papers

• SimHaze: game engine simulated data for real-world dehazing [31.13013422142817]
  We propose an alternative approach for generating paired clean-hazy images by leveraging computer graphics. Using a modern game engine, our approach renders crisp clean images and their precise depth maps, based on which high-quality hazy images can be synthesized for training dehazing models. We show that training with SimHaze alone allows the latest dehazing models to achieve significantly better performance in comparison to previous dehazing datasets.
  arXiv  Detail & Related papers  (2023-05-25T21:26:43Z)
• SCANet: Self-Paced Semi-Curricular Attention Network for Non-Homogeneous Image Dehazing [56.900964135228435]
  Existing homogeneous dehazing methods struggle to handle the non-uniform distribution of haze in a robust manner. We propose a novel self-paced semi-curricular attention network, called SCANet, for non-homogeneous image dehazing. Our approach consists of an attention generator network and a scene reconstruction network.
  arXiv  Detail & Related papers  (2023-04-17T17:05:29Z)
• Single image dehazing via combining the prior knowledge and CNNs [6.566615606042994]
  An end-to-end system is proposed in this paper to reduce defects by combining the prior knowledge and deep learning method. Experiments show that the proposed method achieves superior performance over existing methods.
  arXiv  Detail & Related papers  (2021-11-10T14:18:25Z)
• Non-Homogeneous Haze Removal via Artificial Scene Prior and Bidimensional Graph Reasoning [52.07698484363237]
  We propose a Non-Homogeneous Haze Removal Network (NHRN) via artificial scene prior and bidimensional graph reasoning. Our method achieves superior performance over many state-of-the-art algorithms for both the single image dehazing and hazy image understanding tasks.
  arXiv  Detail & Related papers  (2021-04-05T13:04:44Z)
• 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)
• Nighttime Dehazing with a Synthetic Benchmark [147.21955799938115]
  We propose a novel synthetic method called 3R to simulate nighttime hazy images from daytime clear images. We generate realistic nighttime hazy images by sampling real-world light colors from a prior empirical distribution. Experiment results demonstrate their superiority over state-of-the-art methods in terms of both image quality and runtime.
  arXiv  Detail & Related papers  (2020-08-10T02:16:46Z)
• You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network [63.2086502120071]
  We study how to make deep learning achieve image dehazing without training on the ground-truth clean image (unsupervised) and a image collection (untrained) An unsupervised neural network will avoid the intensive labor collection of hazy-clean image pairs, and an untrained model is a real'' single image dehazing approach. Motivated by the layer disentanglement idea, we propose a novel method, called you only look yourself (textbfYOLY) which could be one of the first unsupervised and untrained neural networks for image dehazing.
  arXiv  Detail & Related papers  (2020-06-30T14:05:47Z)
• 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)
• Self-Supervised Linear Motion Deblurring [112.75317069916579]
  Deep convolutional neural networks are state-of-the-art for image deblurring. We present a differentiable reblur model for self-supervised motion deblurring. Our experiments demonstrate that self-supervised single image deblurring is really feasible.
  arXiv  Detail & Related papers  (2020-02-10T20:15:21Z)

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.