Removing snow from an image via image decomposition

Rajderkar, Dhanashree; Mohod, P. S.

doi:10.1109/ice-ccn.2013.6528565

Cited by 22 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike the characteristics of atmospheric particles in rainy and hazy images that might be described as relatively similar in spatial frequency, trajectory, and translucency, the variations in the particle shape and size of snow makes it more complex. However, existing snow removal methods inherited priors of rainfall-driven features, e.g., HOG [1,25], frequency space separation [26] and color assumptions [30,31] to model falling snow particles. These features not only model just the partial characteristics of snow, but worsen the prospects of generalization.…”

Section: Snow Removalmentioning

confidence: 99%

DesnowNet: Context-Aware Deep Network for Snow Removal

Liu

Jaw

Huang

et al. 2018

IEEE Trans. on Image Process.

175

168

View full text Add to dashboard Cite

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.

show abstract

Section: Snow Removalmentioning

confidence: 99%

DesnowNet: Context-Aware Deep Network for Snow Removal

Liu

Jaw

Huang

et al. 2018

IEEE Trans. on Image Process.

175

168

View full text Add to dashboard Cite

show abstract

“…In this paper, a snow dataset named Snow100K 2 [8] is utilized for training and testing, and it contains synthesized snowy images, relevant clean images and snow masks. We employ 8000 snow masks of disparate scales and 10000 clean background images to generate 18620 synthesized snowy images.…”

Section: A Datasetmentioning

confidence: 99%

“…The low-frequency components were used as the guide graph to remove the rain and snow components from the high-frequency portion. Based on morphological analysis, Rajderkar and Mohod [8] used dictionary learning and sparse representation to detect rain and snow and employed smooth filtering to repair pixels covered by rain and snow. Unfortunately, this method causes image blurring.…”

Section: Introductionmentioning

confidence: 99%

Single-Image Snow Removal Based on an Attention Mechanism and a Generative Adversarial Network

Jia

Yang

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Bad weather, such as snowfall, can seriously decrease the quality of images and pose great challenges to computer vision algorithms. In view of the negative effect of snowfall, this paper presents a single-image snow removal method based on a generative adversarial network (GAN). Unlike previous GANs, our GAN includes an attention mechanism in the generator component. By injecting attention information, the network can pay increased attention to areas covered by snow and improve its capability to perform local repairs. At the same time, we improve the traditional U-Net network by combining it with the residual network to enhance the effect of the model when removing snowflakes from a single image. Our experiments on both synthetic and real-word images show that our method produces better results than those of other state-of-the-art methods.INDEX TERMS Snow removal, generative adversarial networks, attention mechanisms.

show abstract

“…Bossu et al [20] separated the foreground and background by using Gaussian Mixture Model and constructed the snow features in foreground with the Histogram of Orientations of Snow Streaks. Rajderkar et al [29] proposed an image decomposition approach based on Morphological component analysis, where the image would be decomposed into low and high frequency (LF/HF) parts by bilateral filters firstly and then applying dictionary learning and sparse coding methods to identify snow components later. Xu et al [30] modelled snow particles by colour assumptions and removed snow with a guidance image.…”

Section: Snow Removalmentioning

confidence: 99%

“…Rajderkar et al. [29] proposed an image decomposition approach based on Morphological component analysis, where the image would be decomposed into low and high frequency (LF/HF) parts by bilateral filters firstly and then applying dictionary learning and sparse coding methods to identify snow components later. Xu et al.…”

Section: Related Workmentioning

confidence: 99%

Multi‐scale capsule generative adversarial network for snow removal

Yang

Zhang

2021

IET comput. vis

View full text Add to dashboard Cite

Snowflakes captured on photos may severely decrease the visual quality and cause difficulties for vision analysis systems. Most noise removal frameworks are designed for deraining or de-hazing, regarding rain or haze as translucent masks on clean images. However, snowflakes are different from them in terms of sizes, shapes, transparencies and floating trajectories, which decreases the performance of de-raining or de-hazing models in processing snowy images. In this work, we propose an effective multi-scale generative adversarial network framework for single-image snow removal, which is built with a multi-scale structure to identify various scales of snowflakes and a capsulebased structure to fuse the features extracted from the multi-scale encoding branches, so that different scaled features could be summarised and learnt by a joint framework. The overall framework is supervised by a weighted joint loss with an iterative training procedure to keep the training stability for the multi-branch-based structure. The experimental results demonstrate that our model outperforms the state-of-the-art comparisons.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Removing snow from an image via image decomposition

Cited by 22 publications

References 11 publications

DesnowNet: Context-Aware Deep Network for Snow Removal

DesnowNet: Context-Aware Deep Network for Snow Removal

Single-Image Snow Removal Based on an Attention Mechanism and a Generative Adversarial Network

Multi‐scale capsule generative adversarial network for snow removal

Contact Info

Product

Resources

About