FD-GAN: Generative Adversarial Networks with Fusion-discriminator for Single Image Dehazing

By Yu Dong, Yihao Liu, He Zhang, Shifeng Chen, Yu Qiao. AAAI Conference on Artificial Intelligence, 2020

321 citations recorded by the source corpus.

Recently, convolutional neural networks (CNNs) have achieved great improvements in single image dehazing and attained much attention in research. Most existing learning-based dehazing methods are not fully end-to-end, which still follow the traditional dehazing procedure: first estimate the medium transmission and the atmospheric light, then recover the haze-free image based on the atmospheric scattering model. However, in practice, due to lack of priors and constraints, it is hard to precisely estimate these intermediate parameters. Inaccurate estimation further degrades the performance of dehazing, resulting in artifacts, color distortion and insufficient haze removal. To address this, we propose a fully end-to-end Generative Adversarial Networks with Fusion-discriminator (FD-GAN) for image dehazing. With the proposed Fusion-discriminator which takes frequency information as additional priors, our model can generator more natural and realistic dehazed images with less color distortion and fewer artifacts. Moreover, we synthesize a large-scale training dataset including various indoor and outdoor hazy images to boost the performance and we reveal that for learning-based dehazing methods, the performance is strictly influenced by the training data. Experiments have shown that our method reaches state-of-the-art performance on both public synthetic datasets and real-world images with more visually pleasing dehazed results.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/69020e32bf20e0d06f94d611230315b021b33548

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. Peng Hu
2. Boyun Li
3. Jiancheng Lv
4. Xiao Liu
5. Zhongqin Wu
6. Xiaocui Peng

In Media Technology

1. Peng Hu
2. Boyun Li
3. Jiancheng Lv
4. Xiao Liu
5. Zhongqin Wu
6. Xiaocui Peng

Citations in the corpus

• Image Dehazing Transformer with Transmission-Aware 3D Position Embedding (2022, unknown): “In addition to L1 and L2 losses, various losses such as contrastive loss [30] and adversarial loss [8,11] have been used into image dehazing networks.”
• All-In-One Image Restoration for Unknown Corruption (2022, methodology): “To this end, we choose five IRSD methods (i.e., BRDNet [40], LPNet [11], FDGAN [7] and MPRNet [51]) and one IRMD method (i.e., DL [8]) as baselines.”