NH-HAZE: An Image Dehazing Benchmark with Non-Homogeneous Hazy and Haze-Free Images

By Codruta Orniana Ancuti, Cosmin Ancuți, Radu Timofte. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020

475 citations recorded by the source corpus.

Image dehazing is an ill-posed problem that has been extensively studied in the recent years. The objective performance evaluation of the dehazing methods is one of the major obstacles due to the lacking of a reference dataset. While the synthetic datasets have shown important limitations, the few realistic datasets introduced recently assume homogeneous haze over the entire scene. Since in many real cases haze is not uniformly distributed we introduce NH-HAZE, a non-homogeneous realistic dataset with pairs of real hazy and corresponding haze-free images. This is the first nonhomogeneous image dehazing dataset and contains 55 outdoor scenes. The non-homogeneous haze has been introduced in the scene using a professional haze generator that imitates the real conditions of hazy scenes. Additionally, this work presents an objective assessment of several state- of-the-art single image dehazing methods that were evaluated using NH-HAZE dataset.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/88e8a624825f0fb457fac26f65d43d9da76beab0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Chongyi Li
2. Chunle Guo
3. Runmin Cong
4. Wenqi Ren
5. Saeed Anwar
6. Yanyun Qu
7. Yuan Xie
8. Yuda Song

In Media Technology

1. Runmin Cong
2. Chunle Guo
3. Chongyi Li
4. Yanyun Qu
5. Yuan Xie
6. Wenqi Ren
7. Saeed Anwar
8. Yuda Song

Citations in the corpus

• Image Dehazing Transformer with Transmission-Aware 3D Position Embedding (2022, methodology): “To further validate the performance of our method, we compare different methods on real hazy images sampled from Dense-Haze and NH-HAZE testing sets.”
• Vision Transformers for Single Image Dehazing (2022, methodology): “These dehazing datasets are divided into two main categories: real datasets [47], [50],”
• Contrastive Learning for Compact Single Image Dehazing (2021, methodology): “Method SOTS [27] Dense-Haze [1] NH-HAZE [2] # Param PSNR SSIM PSNR SSIM PSNR SSIM”