DesnowNet: Context-Aware Deep Network for Snow Removal

By Yun-Fu Liu, Da-Wei Jaw, Shih-Chia Huang, Jenq-Neng Hwang. IEEE Transactions on Image Processing, 2017

508 citations recorded by the source corpus.

Existing learning-based atmospheric particle-removal approaches such as those used for rainy and hazy images are designed with strong assumptions regarding spatial frequency, trajectory, and translucency. However, the removal of snow particles is more complicated because they possess additional attributes of particle size and shape, and these attributes may vary within a single image. Currently, hand-crafted features are still the mainstream for snow removal, making significant generalization difficult to achieve. In response, we have designed a multistage network named DesnowNet to in turn deal with the removal of translucent and opaque snow particles. We also differentiate snow attributes of translucency and chromatic aberration for accurate estimation. Moreover, our approach individually estimates residual complements of the snow-free images to recover details obscured by opaque snow. Additionally, a multi-scale design is utilized throughout the entire network to model the diversity of snow. As demonstrated in the qualitative and quantitative experiments, our approach outperforms state-of-the-art learning-based atmospheric phenomena removal methods and one semantic segmentation baseline on the proposed Snow100K dataset. The results indicate our network would benefit applications involving computer vision and graphics.

Subfields: Atmospheric Science, Computer Vision and Pattern Recognition, Global and Planetary Change

View Paper: https://www.semanticscholar.org/paper/9e7487d7396acf298f972f0b8ab0397e0d9e7a0f

How researchers see this paper

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

In Atmospheric Science

1. Vishal M. Patel
2. David Vázquez
3. Robert A. Legenstein
4. Ozan Özdenizci

In Computer Vision and Pattern Recognition

1. Vishal M. Patel
2. Rajeev Yasarla
3. Robert A. Legenstein
4. Ozan Özdenizci
5. Jeya Maria Jose Valanarasu
6. Luc Van Gool
7. Loong Fah Cheong
8. Ruoteng Li

In Global and Planetary Change

1. Vishal M. Patel
2. Robert A. Legenstein
3. Ozan Özdenizci

Citations in the corpus

• All in One Bad Weather Removal Using Architectural Search (2020, methodology): “We train our network on different bad weather datasets, including “Outdoor-Rain” [25], “Snow100K” [38], and “Raindrop” [41].”
• Learning to Remove Rain in Traffic Surveillance by using Synthetic Data (2019, methodology): “A CNN containing dilated convolutions were used in (Yang et al., 2017) whereas Liu et al. (2017) used a network based on the Inception V4 architecture (Szegedy et al., 2017).”
• TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions (2021, methodology): “Adverse weather removal problems like deraining [16, 21,25,51,61,65,76], dehazing [1,2,10,22,42,69], desnowing [29,44,44,73] and rain drop removal [37,39,40,66] have been extensively explored in the literature.”
• ALL Snow Removed: Single Image Desnowing Algorithm Using Hierarchical Dual-tree Complex Wavelet Representation and Contradict Channel Loss (2021, methodology): “They proposed the first snow dataset called Snow-100K.”
• Restoring Vision in Adverse Weather Conditions With Patch-Based Denoising Diffusion Models (2022, methodology): “It also contains additional 1,329 real snowy images (Snow100K-Real) to evaluate real-world generalization of models trained with synthetic data.”