FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2580458810> ?p ?o ?g. }

• W2580458810 abstract "Severe weather conditions such as rain and snow adversely affect the visual quality of images captured under such conditions thus rendering them useless for further usage and sharing. In addition, such degraded images drastically affect performance of vision systems. Hence, it is important to solve the problem of single image de-raining/de-snowing. However, this is a difficult problem to solve due to its inherent ill-posed nature. Existing approaches attempt to introduce prior information to convert it into a well-posed problem. In this paper, we investigate a new point of view in addressing the single image de-raining problem. Instead of focusing only on deciding what is a good prior or a good framework to achieve good quantitative and qualitative performance, we also ensure that the de-rained image itself does not degrade the performance of a given computer vision algorithm such as detection and classification. In other words, the de-rained result should be indistinguishable from its corresponding clear image to a given discriminator. This criterion can be directly incorporated into the optimization framework by using the recently introduced conditional generative adversarial networks (GANs). To minimize artifacts introduced by GANs and ensure better visual quality, a new refined loss function is introduced. Based on this, we propose a novel single image de-raining method called Image De-raining Conditional General Adversarial Network (ID-CGAN), which considers quantitative, visual and also discriminative performance into the objective function. Experiments evaluated on synthetic images and real images show that the proposed method outperforms many recent state-of-the-art single image de-raining methods in terms of quantitative and visual performance." @default.
• W2580458810 created "2017-02-03" @default.
• W2580458810 creator A5004716468 @default.
• W2580458810 creator A5036034054 @default.
• W2580458810 creator A5064323494 @default.
• W2580458810 date "2017-01-20" @default.
• W2580458810 modified "2023-09-27" @default.
• W2580458810 title "Image De-raining Using a Conditional Generative Adversarial Network" @default.
• W2580458810 cites W1522301498 @default.
• W2580458810 cites W1686810756 @default.
• W2580458810 cites W1901129140 @default.
• W2580458810 cites W1903029394 @default.
• W2580458810 cites W1905829557 @default.
• W2580458810 cites W1924619199 @default.
• W2580458810 cites W1965572510 @default.
• W2580458810 cites W1972568768 @default.
• W2580458810 cites W1981337995 @default.
• W2580458810 cites W1992687477 @default.
• W2580458810 cites W2004346156 @default.
• W2580458810 cites W2046119925 @default.
• W2580458810 cites W2096933452 @default.
• W2580458810 cites W2099471712 @default.
• W2580458810 cites W2110158442 @default.
• W2580458810 cites W2113569611 @default.
• W2580458810 cites W2119535410 @default.
• W2580458810 cites W2121396509 @default.
• W2580458810 cites W2121651107 @default.
• W2580458810 cites W2125389028 @default.
• W2580458810 cites W2133665775 @default.
• W2580458810 cites W2146337213 @default.
• W2580458810 cites W2154621477 @default.
• W2580458810 cites W2154815154 @default.
• W2580458810 cites W2154996879 @default.
• W2580458810 cites W2159269332 @default.
• W2580458810 cites W2173520492 @default.
• W2580458810 cites W2194775991 @default.
• W2580458810 cites W2209874411 @default.
• W2580458810 cites W2259643685 @default.
• W2580458810 cites W2273348943 @default.
• W2580458810 cites W2330127310 @default.
• W2580458810 cites W2339754110 @default.
• W2580458810 cites W2342877626 @default.
• W2580458810 cites W2466666260 @default.
• W2580458810 cites W2503339013 @default.
• W2580458810 cites W2509784253 @default.
• W2580458810 cites W2520164769 @default.
• W2580458810 cites W2521028896 @default.
• W2580458810 cites W2525037006 @default.
• W2580458810 cites W2525063107 @default.
• W2580458810 cites W2557969682 @default.
• W2580458810 cites W2559264300 @default.
• W2580458810 cites W2559991484 @default.
• W2580458810 cites W2560023338 @default.
• W2580458810 cites W2564591810 @default.
• W2580458810 cites W2609887106 @default.
• W2580458810 cites W2613034492 @default.
• W2580458810 cites W2613718673 @default.
• W2580458810 cites W2613955579 @default.
• W2580458810 cites W2731516742 @default.
• W2580458810 cites W2740982616 @default.
• W2580458810 cites W2777170053 @default.
• W2580458810 cites W2777241530 @default.
• W2580458810 cites W2784790939 @default.
• W2580458810 cites W2798617638 @default.
• W2580458810 cites W2799215068 @default.
• W2580458810 cites W2803796574 @default.
• W2580458810 cites W2884585535 @default.
• W2580458810 cites W2888632407 @default.
• W2580458810 cites W2949999304 @default.
• W2580458810 cites W2950689937 @default.
• W2580458810 cites W2951446714 @default.
• W2580458810 cites W2962825119 @default.
• W2580458810 cites W2963073614 @default.
• W2580458810 cites W2963306157 @default.
• W2580458810 cites W2963373786 @default.
• W2580458810 cites W2963413689 @default.
• W2580458810 cites W2963446712 @default.
• W2580458810 cites W2963468256 @default.
• W2580458810 cites W2963470893 @default.
• W2580458810 cites W2963784072 @default.
• W2580458810 cites W2963878020 @default.
• W2580458810 cites W2963966654 @default.
• W2580458810 cites W2964024144 @default.
• W2580458810 cites W2964212750 @default.
• W2580458810 cites W3106370837 @default.
• W2580458810 cites W753012316 @default.
• W2580458810 cites W845365781 @default.
• W2580458810 doi "https://doi.org/10.48550/arxiv.1701.05957" @default.
• W2580458810 hasPublicationYear "2017" @default.
• W2580458810 type Work @default.
• W2580458810 sameAs 2580458810 @default.
• W2580458810 citedByCount "23" @default.
• W2580458810 countsByYear W25804588102017 @default.
• W2580458810 countsByYear W25804588102018 @default.
• W2580458810 countsByYear W25804588102019 @default.
• W2580458810 countsByYear W25804588102020 @default.
• W2580458810 crossrefType "posted-content" @default.
• W2580458810 hasAuthorship W2580458810A5004716468 @default.
• W2580458810 hasAuthorship W2580458810A5036034054 @default.
• W2580458810 hasAuthorship W2580458810A5064323494 @default.

• next