DehazeZoo:图像&视频去雾清晰化资源大全(论文/数据集/开源项目)
图像去雾的目的是消除雾霾环境对图像质量的影响,增加图像的可视度,是图像处理和计算机视觉领域共同关切的前沿课题,吸引了国内外研究人员的广泛关注。在github上 cxtalk列举了图像去雾近年来经典论文、评估指标与数据集,在此转载以便记录。
转载自:DehazeZoo (Single Image vs. Video Based) https://github.com/cxtalk/DehazeZoo
DehazeZoo (Single Image vs. Video Based)
Xiang Chen, Yufeng Li, Yufeng Huang
1 Description
-
DehazeZoo: A survey on haze removal from video and single image. Papers, codes and datasets are maintained.
-
Thanks for the sharing of DerainZoo by Youzhao Yang.
-
More details about image dehazing and deraining are available here.
2 Image Quality Metrics
- PSNR (Peak Signal-to-Noise Ratio) [paper] [matlab code] [python code]
- SSIM (Structural Similarity) [paper] [matlab code] [python code]
- VIF (Visual Quality) [paper] [matlab code]
- FSIM (Feature Similarity) [paper] [matlab code]
- NIQE (Naturalness Image Quality Evaluator) [paper][matlab code][python code]
3 Dehazing Research
3.1 Datasets
- KITTI [paper][dataset]
- RESIDE [paper][dataset]
- SceneNet [paper][dataset]
- I-HAZE [paper][dataset]
- O-HAZE [paper][dataset]
- D-HAZY [paper][dataset]
- Middlebury [paper][dataset]
- NYU Depth Dataset V2 [paper][dataset]
3.2 Papers
2020
- Shen et al, Implicit Euler ODE Networks for Single-Image Dehazing. [paper][code]
- Liu et al, Efficient Unpaired Image Dehazing with Cyclic Perceptual-Depth Supervision. [paper][code]
- Li et al, You Only Look Yourself: Unsupervised and Untrained Single Image Dehazing Neural Network. [paper][code]
- Pang et al, BidNet: Binocular Image Dehazing without Explicit Disparity Estimation. (CVPR) [paper][code]
- Sourya et al, Fast Deep Multi-patch Hierarchical Network for Nonhomogeneous Image Dehazing. [paper][code]
- Dong et al, Multi-Scale Boosted Dehazing Network with Dense Feature Fusion. (CVPR) [paper][code]
- Li et al, Learning to Dehaze From Realistic Scene with A Fast Physics Based Dehazing Network. [paper][code]
- Shao et al, Domain Adaptation for Image Dehazing. (CVPR) [paper][code][web]
- Wu et al, Accurate Transmission Estimation for Removing Haze and Noise from a Single Image. (TIP) [paper][code]
- Ren et al, Single Image Dehazing via Multi-Scale Convolutional Neural Networks with Holistic Edges. (IJCV) [paper][code]
- Dong et al, FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing. [paper][code]
- Qin et al, FFA-Net: Feature Fusion Attention Network for Single Image Dehazing. (AAAI) [paper][code]
2019
- Wu et al, Learning Interleaved Cascade of Shrinkage Fields for Joint Image Dehazing and Denoising. (TIP) [paper][code]
- Li et al, Semi-Supervised Image Dehazing. (TIP) [paper][code]
- Li et al, Benchmarking Single Image Dehazing and Beyond. (TIP) [paper][code][web]
- Pei et al, Classification-driven Single Image Dehazing. [paper][code]
- Liu et al, GridDehazeNet: Attention-Based Multi-Scale Network for Image Dehazing. (ICCV) [paper][code]
- Li et al, Joint haze image synthesis and dehazing with mmd-vae losses. [paper][code]
- Peter et al, Feature Forwarding for Efficient Single Image Dehazing. [paper][code]
- Shu et al, Variational Regularized Transmission Refinement for Image Dehazing. [paper][code]
- Liu et al, End-to-End Single Image Fog Removal using Enhanced Cycle Consistent Adversarial Networks. [paper][code]
- Chen et al, Gated Context Aggregation Network for Image Dehazing and Deraining. (WACV) [paper][code]
- Ren et al, Deep Video Dehazing with Semantic Segmentation. (TIP) [paper][code]
2018
- Ren et al, Gated Fusion Network for Single Image Dehazing. (CVPR) [paper][code][web]
- Zhang et al, FEED-Net: Fully End-To-End Dehazing. (ICME) [paper][code]
- Zhang et al, Densely Connected Pyramid Dehazing Network. (CVPR) [paper][code]
- Yang et al, Towards Perceptual Image Dehazing by Physics-based Disentanglement and Adversarial Training. (AAAI) [paper][code]
- Deniz et al, Cycle-Dehaze: Enhanced CycleGAN for Single Image Dehazing. (CVPRW) [paper][code]
Before
- Ren et al, An All-in-One Network for Dehazing and Beyond. (ICCV) [paper][code][web]
- Zhu et al, Single Image Dehazing via Multi-Scale Convolutional Neural Networks. (ECCV) [paper][code][web]
- Cai et al, DehazeNet: An end-to-end system for single image haze removal. (TIP) [paper][code][web]
- Ren et al, A fast single image haze removal algorithm using color attenuation prior. (TIP) [paper][code]
- He et al, Single Image Haze Removal Using Dark Channel Prior. (CVPR) [paper][code]
4 Note
- The above content is constantly updated, welcome continuous attention!
5 Acknowledgement
- Thanks for the sharing of codes of image quality metrics by Wang, Hong.
6 Contact
- If you have any question, please feel free to contact Xiang Chen (Email: cx@cvgpu.com).
- 原文作者:jchen
- 原文链接:http://jchenTech.github.io/post/%E5%9B%BE%E5%83%8F%E5%A4%84%E7%90%86%E4%B8%8E%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/%E5%9B%BE%E5%83%8F%E5%8E%BB%E9%9B%BE%E7%BB%8F%E5%85%B8%E8%AE%BA%E6%96%87%E4%B8%8E%E6%95%B0%E6%8D%AE%E9%9B%86/
- 版权声明:本作品采用知识共享署名-非商业性使用-禁止演绎 4.0 国际许可协议进行许可,非商业转载请注明出处(作者,原文链接),商业转载请联系作者获得授权。