Matches in SemOpenAlex for { <https://semopenalex.org/work/W3169078099> ?p ?o ?g. }
- W3169078099 abstract "For the single image rain removal (SIRR) task, the performance of deep learning (DL)-based methods is mainly affected by the designed deraining models and training datasets. Most of current state-of-the-art focus on constructing powerful deep models to obtain better deraining results. In this paper, to further improve the deraining performance, we novelly attempt to handle the SIRR task from the perspective of training datasets by exploring a more efficient way to synthesize rainy images. Specifically, we build a full Bayesian generative model for rainy image where the rain layer is parameterized as a generator with the input as some latent variables representing the physical structural rain factors, e.g., direction, scale, and thickness. To solve this model, we employ the variational inference framework to approximate the expected statistical distribution of rainy image in a data-driven manner. With the learned generator, we can automatically and sufficiently generate diverse and non-repetitive training pairs so as to efficiently enrich and augment the existing benchmark datasets. User study qualitatively and quantitatively evaluates the realism of generated rainy images. Comprehensive experiments substantiate that the proposed model can faithfully extract the complex rain distribution that not only helps significantly improve the deraining performance of current deep single image derainers, but also largely loosens the requirement of large training sample pre-collection for the SIRR task. Code is available in https://github.com/hongwang01/VRGNet." @default.
- W3169078099 created "2021-06-22" @default.
- W3169078099 creator A5022673825 @default.
- W3169078099 creator A5033020983 @default.
- W3169078099 creator A5038174569 @default.
- W3169078099 creator A5051649145 @default.
- W3169078099 creator A5065256379 @default.
- W3169078099 creator A5091017287 @default.
- W3169078099 date "2021-06-01" @default.
- W3169078099 modified "2023-10-18" @default.
- W3169078099 title "From Rain Generation to Rain Removal" @default.
- W3169078099 cites W1965572510 @default.
- W3169078099 cites W1986266272 @default.
- W3169078099 cites W2114770744 @default.
- W3169078099 cites W2127498532 @default.
- W3169078099 cites W2131787037 @default.
- W3169078099 cites W2132103241 @default.
- W3169078099 cites W2133665775 @default.
- W3169078099 cites W2150066425 @default.
- W3169078099 cites W2466666260 @default.
- W3169078099 cites W2509784253 @default.
- W3169078099 cites W2559264300 @default.
- W3169078099 cites W2740982616 @default.
- W3169078099 cites W2780930362 @default.
- W3169078099 cites W2798278116 @default.
- W3169078099 cites W2798401637 @default.
- W3169078099 cites W2887181327 @default.
- W3169078099 cites W2906196996 @default.
- W3169078099 cites W2912435603 @default.
- W3169078099 cites W2913360047 @default.
- W3169078099 cites W2930755307 @default.
- W3169078099 cites W2954171777 @default.
- W3169078099 cites W2963017889 @default.
- W3169078099 cites W2963312584 @default.
- W3169078099 cites W2963800716 @default.
- W3169078099 cites W2963866045 @default.
- W3169078099 cites W2963878020 @default.
- W3169078099 cites W2964212750 @default.
- W3169078099 cites W2964267765 @default.
- W3169078099 cites W2966083079 @default.
- W3169078099 cites W2967584026 @default.
- W3169078099 cites W2970842755 @default.
- W3169078099 cites W2991350899 @default.
- W3169078099 cites W2998545307 @default.
- W3169078099 cites W2999659739 @default.
- W3169078099 cites W3009606699 @default.
- W3169078099 cites W3028045870 @default.
- W3169078099 cites W3034242291 @default.
- W3169078099 cites W3035250394 @default.
- W3169078099 cites W3035326127 @default.
- W3169078099 cites W3035713416 @default.
- W3169078099 cites W3095516474 @default.
- W3169078099 cites W3097364975 @default.
- W3169078099 doi "https://doi.org/10.1109/cvpr46437.2021.01455" @default.
- W3169078099 hasPublicationYear "2021" @default.
- W3169078099 type Work @default.
- W3169078099 sameAs 3169078099 @default.
- W3169078099 citedByCount "33" @default.
- W3169078099 countsByYear W31690780992021 @default.
- W3169078099 countsByYear W31690780992022 @default.
- W3169078099 countsByYear W31690780992023 @default.
- W3169078099 crossrefType "proceedings-article" @default.
- W3169078099 hasAuthorship W3169078099A5022673825 @default.
- W3169078099 hasAuthorship W3169078099A5033020983 @default.
- W3169078099 hasAuthorship W3169078099A5038174569 @default.
- W3169078099 hasAuthorship W3169078099A5051649145 @default.
- W3169078099 hasAuthorship W3169078099A5065256379 @default.
- W3169078099 hasAuthorship W3169078099A5091017287 @default.
- W3169078099 hasBestOaLocation W31690780992 @default.
- W3169078099 hasConcept C11413529 @default.
- W3169078099 hasConcept C115961682 @default.
- W3169078099 hasConcept C119857082 @default.
- W3169078099 hasConcept C120665830 @default.
- W3169078099 hasConcept C121332964 @default.
- W3169078099 hasConcept C124101348 @default.
- W3169078099 hasConcept C13280743 @default.
- W3169078099 hasConcept C153294291 @default.
- W3169078099 hasConcept C154945302 @default.
- W3169078099 hasConcept C162324750 @default.
- W3169078099 hasConcept C163258240 @default.
- W3169078099 hasConcept C165464430 @default.
- W3169078099 hasConcept C167966045 @default.
- W3169078099 hasConcept C177264268 @default.
- W3169078099 hasConcept C185592680 @default.
- W3169078099 hasConcept C185798385 @default.
- W3169078099 hasConcept C187736073 @default.
- W3169078099 hasConcept C192209626 @default.
- W3169078099 hasConcept C198531522 @default.
- W3169078099 hasConcept C199360897 @default.
- W3169078099 hasConcept C205649164 @default.
- W3169078099 hasConcept C2776760102 @default.
- W3169078099 hasConcept C2777211547 @default.
- W3169078099 hasConcept C2780451532 @default.
- W3169078099 hasConcept C2780992000 @default.
- W3169078099 hasConcept C39890363 @default.
- W3169078099 hasConcept C41008148 @default.
- W3169078099 hasConcept C43617362 @default.
- W3169078099 hasConcept C62520636 @default.
- W3169078099 hasConceptScore W3169078099C11413529 @default.
- W3169078099 hasConceptScore W3169078099C115961682 @default.