Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204296306> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3204296306 abstract "We present a simple yet effective unpaired learning based image rain removal method from an unpaired set of synthetic images and real rainy images by exploring the properties of rain maps. The proposed algorithm mainly consists of a semi-supervised learning part and a knowledge distillation part. The semi-supervised part estimates the rain map and reconstructs the derained image based on the well-established layer separation principle. To facilitate rain removal, we develop a rain direction regularizer to constrain the rain estimation network in the semi-supervised learning part. With the estimated rain maps from the semi-supervised learning part, we first synthesize a new paired set by adding to rain-free images based on the superimposition model. The real rainy images and the derained results constitute another paired set. Then we develop an effective knowledge distillation method to explore such two paired sets so that the deraining model in the semi-supervised learning part is distilled. We propose two new rainy datasets, named RainDirection and Real3000, to validate the effectiveness of the proposed method. Both quantitative and qualitative experimental results demonstrate that the proposed method achieves favorable results against state-of-the-art methods in benchmark datasets and real-world images." @default.
- W3204296306 created "2021-10-11" @default.
- W3204296306 creator A5004164569 @default.
- W3204296306 creator A5013672400 @default.
- W3204296306 creator A5023363049 @default.
- W3204296306 creator A5053622281 @default.
- W3204296306 date "2021-10-01" @default.
- W3204296306 modified "2023-09-25" @default.
- W3204296306 title "Unpaired Learning for Deep Image Deraining with Rain Direction Regularizer" @default.
- W3204296306 cites W2102166818 @default.
- W3204296306 cites W2154621477 @default.
- W3204296306 cites W2194775991 @default.
- W3204296306 cites W2209874411 @default.
- W3204296306 cites W2466666260 @default.
- W3204296306 cites W2509784253 @default.
- W3204296306 cites W2739757502 @default.
- W3204296306 cites W2740982616 @default.
- W3204296306 cites W2789288870 @default.
- W3204296306 cites W2912435603 @default.
- W3204296306 cites W2913360047 @default.
- W3204296306 cites W2930755307 @default.
- W3204296306 cites W2962785568 @default.
- W3204296306 cites W2963372104 @default.
- W3204296306 cites W2963641969 @default.
- W3204296306 cites W2963725279 @default.
- W3204296306 cites W2963878020 @default.
- W3204296306 cites W2964212750 @default.
- W3204296306 cites W2980047233 @default.
- W3204296306 cites W3026432413 @default.
- W3204296306 cites W3034242291 @default.
- W3204296306 cites W3035326127 @default.
- W3204296306 cites W3035557850 @default.
- W3204296306 cites W3035713416 @default.
- W3204296306 doi "https://doi.org/10.1109/iccv48922.2021.00471" @default.
- W3204296306 hasPublicationYear "2021" @default.
- W3204296306 type Work @default.
- W3204296306 sameAs 3204296306 @default.
- W3204296306 citedByCount "11" @default.
- W3204296306 countsByYear W32042963062022 @default.
- W3204296306 countsByYear W32042963062023 @default.
- W3204296306 crossrefType "proceedings-article" @default.
- W3204296306 hasAuthorship W3204296306A5004164569 @default.
- W3204296306 hasAuthorship W3204296306A5013672400 @default.
- W3204296306 hasAuthorship W3204296306A5023363049 @default.
- W3204296306 hasAuthorship W3204296306A5053622281 @default.
- W3204296306 hasConcept C115961682 @default.
- W3204296306 hasConcept C119857082 @default.
- W3204296306 hasConcept C127313418 @default.
- W3204296306 hasConcept C13280743 @default.
- W3204296306 hasConcept C136389625 @default.
- W3204296306 hasConcept C153180895 @default.
- W3204296306 hasConcept C154945302 @default.
- W3204296306 hasConcept C177264268 @default.
- W3204296306 hasConcept C185798385 @default.
- W3204296306 hasConcept C199360897 @default.
- W3204296306 hasConcept C41008148 @default.
- W3204296306 hasConcept C50644808 @default.
- W3204296306 hasConceptScore W3204296306C115961682 @default.
- W3204296306 hasConceptScore W3204296306C119857082 @default.
- W3204296306 hasConceptScore W3204296306C127313418 @default.
- W3204296306 hasConceptScore W3204296306C13280743 @default.
- W3204296306 hasConceptScore W3204296306C136389625 @default.
- W3204296306 hasConceptScore W3204296306C153180895 @default.
- W3204296306 hasConceptScore W3204296306C154945302 @default.
- W3204296306 hasConceptScore W3204296306C177264268 @default.
- W3204296306 hasConceptScore W3204296306C185798385 @default.
- W3204296306 hasConceptScore W3204296306C199360897 @default.
- W3204296306 hasConceptScore W3204296306C41008148 @default.
- W3204296306 hasConceptScore W3204296306C50644808 @default.
- W3204296306 hasFunder F4320321001 @default.
- W3204296306 hasLocation W32042963061 @default.
- W3204296306 hasOpenAccess W3204296306 @default.
- W3204296306 hasPrimaryLocation W32042963061 @default.
- W3204296306 hasRelatedWork W2939912336 @default.
- W3204296306 hasRelatedWork W3046775127 @default.
- W3204296306 hasRelatedWork W3094076422 @default.
- W3204296306 hasRelatedWork W3162567751 @default.
- W3204296306 hasRelatedWork W4220686584 @default.
- W3204296306 hasRelatedWork W4221088574 @default.
- W3204296306 hasRelatedWork W4285260836 @default.
- W3204296306 hasRelatedWork W4288373736 @default.
- W3204296306 hasRelatedWork W4312365371 @default.
- W3204296306 hasRelatedWork W4319309271 @default.
- W3204296306 isParatext "false" @default.
- W3204296306 isRetracted "false" @default.
- W3204296306 magId "3204296306" @default.
- W3204296306 workType "article" @default.