• Corpus ID: 4930540

Semantic Single-Image Dehazing

@article{Cheng2018SemanticSD,
  title={Semantic Single-Image Dehazing},
  author={Ziang Cheng and Shaodi You and Viorela Ila and Hongdong Li},
  journal={ArXiv},
  year={2018},
  volume={abs/1804.05624}
}
Single-image haze-removal is challenging due to limited information contained in one single image. Previous solutions largely rely on handcrafted priors to compensate for this deficiency. Recent convolutional neural network (CNN) models have been used to learn haze-related priors but they ultimately work as advanced image filters. In this paper we propose a novel semantic ap- proach towards single image haze removal. Unlike existing methods, we infer color priors based on extracted semantic… 

Figures and Tables from this paper

Semantic-Aware Dehazing Network With Adaptive Feature Fusion

It is shown that it is possible to recover textures faithfully by incorporating semantic prior into dehazing network since objects in haze-free images tend to show certain shapes, textures, and colors.

Deep Video Dehazing With Semantic Segmentation

This paper develops a deep learning solution for video dehazing, where a CNN is trained end-to-end to learn how to accumulate information across frames for transmission estimation, and proposes to incorporate global semantic priors as input to regularize the transmission maps.

The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing

A novel deep neural network architecture for the challenging problem of single image dehazing, which aims to recover the clear image from a degraded hazy image, which outperforms the state-of-the-art methods by a large margin on the benchmark datasets.

High-Resolution Single Image Dehazing Using Encoder-Decoder Architecture

Quantitative results on the recently released DenseHaze dataset introduced for the NTIRE2019-Dehazing challenge demonstrates the effectiveness of the proposed HR-DeHazer method, and qualitative results on real data show that the described solution generalizes well to different never-seen scenarios.

Deep Multi-Model Fusion for Single-Image Dehazing

  • Zijun DengLei Zhu P. Heng
  • Computer Science
    2019 IEEE/CVF International Conference on Computer Vision (ICCV)
  • 2019
A deep multi-model fusion network to attentively integrate multiple models to separate layers and boost the performance in single-image dehazing is presented.

Single Image Dehazing: An Analysis on Generative Adversarial Network

A comprehensive study on three single image dehazing state-of-the-art GAN models, such as AOD-Net, cGAN, and DHSGAN, which shows the DHSGAN gives the best performance.

Pyramid Global Context Network for Image Dehazing

The finalized dehazing model can explore both long-range and patch-wise context dependencies for global context modeling, which is crucial for image dehazed.

Deep Dense Multi-Scale Network for Snow Removal Using Semantic and Depth Priors

This paper proposes a Deep Dense Multi-Scale Network for snow removal by exploiting semantic and geometric priors, and designs a DDMSNet to learn semantic-aware and geometry-aware representation via a self-attention mechanism to produce the final clean images.

Implicit Euler ODE Networks for Single-Image Dehazing

This paper proposes an efficient end-to-end multi-level implicit network (MI-Net) for the single image dehazing problem, and outperforms existing methods and achieves the state-of-the-art performance.

Image Dehazing using Dark and Bright Channel Priors and Multi-scale Filters

The paper proposes bright and dark channel priors dependent single image based dehazing in two color spaces. The hazy RGB is first converted into YCbCr space. Transmission maps are estimated using

References

SHOWING 1-10 OF 33 REFERENCES

Investigating Haze-Relevant Features in a Learning Framework for Image Dehazing

It is shown that the dark-channel feature is the most informative one for this task, which confirms the observation of He et al.

Robust Image and Video Dehazing with Visual Artifact Suppression via Gradient Residual Minimization

A new method for reliable suppression of different types of visual artifacts in image and video dehazing is proposed and can generate results with much less visual artifacts than previous approaches for lower quality inputs such as compressed video clips.

DehazeNet: An End-to-End System for Single Image Haze Removal

This paper proposes a trainable end-to-end system called DehazeNet, for medium transmission estimation, which takes a hazy image as input, and outputs its medium transmission map that is subsequently used to recover a haze-free image via atmospheric scattering model.

Towards Perceptual Image Dehazing by Physics-Based Disentanglement and Adversarial Training

This work proposes Disentangled Dehazing Network, an end-to-end model that generates realistic haze-free images using only unpaired supervision by introducing a physical-model based disentanglement and reconstruction mechanism.

Single Image Dehazing via Multi-scale Convolutional Neural Networks

A multi-scale deep neural network for single-image dehazing by learning the mapping between hazy images and their corresponding transmission maps by combining a coarse-scale net which predicts a holistic transmission map based on the entire image, and a fine-scale network which refines results locally.

A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior

A simple but powerful color attenuation prior for haze removal from a single input hazy image is proposed and outperforms state-of-the-art haze removal algorithms in terms of both efficiency and the dehazing effect.

D-HAZY: A dataset to evaluate quantitatively dehazing algorithms

A dataset that contains 1400+ pairs of images with ground truth reference images and hazy images of the same scene, built on the Middelbury and NYU Depth datasets that provide images of various scenes and their corresponding depth maps is introduced.

AOD-Net: All-in-One Dehazing Network

An image dehazing model built with a convolutional neural network (CNN) based on a re-formulated atmospheric scattering model, called All-in-One Dehazing Network (AOD-Net), which demonstrates superior performance than the state-of-the-art in terms of PSNR, SSIM and the subjective visual quality.

Non-local Image Dehazing

This work proposes an algorithm, linear in the size of the image, deterministic and requires no training, that performs well on a wide variety of images and is competitive with other state-of-the-art methods on the single image dehazing problem.

Dehazing Using Color-Lines

A new method for single-image dehazing that relies on a generic regularity in natural images where pixels of small image patches typically exhibit a 1D distribution in RGB color space, known as color-lines is described.