JSTASR: Joint Size and Transparency-Aware Snow Removal Algorithm Based on Modified Partial Convolution and Veiling Effect Removal

Chen, Weiting; Fang, Haoyu; Ding, Jian-Jiun; Tsai, Cheng-Che; Kuo, Sy‐Yen

doi:10.1007/978-3-030-58589-1_45

Cited by 89 publications

(123 citation statements)

References 30 publications

Supporting

Mentioning

122

Contrasting

Order By: Relevance

“…Fig. 8 shows the results obtained by the algorithms of Wang et al [9], Chen et al [17], and Yang et al [38] in comparison with our results. As seen from Fig.…”

Section: ) Qualitative Evaluationsupporting

confidence: 51%

“…We utilize processing time per image to present the run time complexity. As shown in Table 3, the method of Yang et al [38] has the fastest processing time, while the method of Chen et al [17] has the slowest. Our method is slower than the methods of Wang et al [9] and Yang et al [38], but faster than other competing algorithms.…”

Section: ) Quantitative Evaluationmentioning

confidence: 99%

“…In this section, we show the qualitative evaluation of the performances of the proposed method and the methods of Wang et al [9], Chen et al [17], Qian et al [36], and Yang et al [38]. We conduct experiments on both the synthetic images and the real image to provide convincing results.…”

Section: ) Qualitative Evaluationmentioning

confidence: 99%

“…Some snowflake pixels have not been completely fixed, as the second group image shows. The algorithm of Chen et al [17] removes some snowflakes while some snow remains. Unfortunately, images processed by the method of Chen et al [17] lose the details and produce some artifacts, which are obvious in the third group image.…”

Section: ) Qualitative Evaluationmentioning

confidence: 99%

“…In this way, snowflake detection and removal were achieved. Chen et al [17] proposed a joint size and transparency-aware snow removal method of joint size that can address both transparent and nontransparent snow particles by applying the modified partial convolution. Yang et al [18] proposed a deep-learning-based rain streak removal method injected with self-supervision.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

“…Fig. 8 shows the results obtained by the algorithms of Wang et al [9], Chen et al [17], and Yang et al [38] in comparison with our results. As seen from Fig.…”

Section: ) Qualitative Evaluationsupporting

confidence: 51%