Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204752223> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3204752223 abstract "Barrel distortion rectification aims at removing the radial distortion in a distorted image captured by a wide-angle lens. Previous deep learning methods mainly solve this problem by learning the implicit distortion parameters or the nonlinear rectified mapping function in a direct manner. However, this type of manner results in an indistinct learning process of rectification and thus limits the deep perception of distortion. In this paper, inspired by the curriculum learning, we analyze the barrel distortion rectification task in a progressive and meaningful manner. By considering the relationship among different construction levels in an image, we design a multi-level curriculum that disassembles the rectification task into three levels, structure recovery, semantics embedding, and texture rendering. With the guidance of the curriculum that corresponds to the construction of images, the proposed hierarchical architecture enables a progressive rectification and achieves more accurate results. Moreover, we present a novel distortion-aware pre-training strategy to facilitate the initial learning of neural networks, promoting the model to converge faster and better. Experimental results on the synthesized and real-world distorted image datasets show that the proposed approach significantly outperforms other learning methods, both qualitatively and quantitatively." @default.
- W3204752223 created "2021-10-11" @default.
- W3204752223 creator A5028127027 @default.
- W3204752223 creator A5050402282 @default.
- W3204752223 creator A5059372830 @default.
- W3204752223 creator A5069893831 @default.
- W3204752223 creator A5080547175 @default.
- W3204752223 date "2021-10-01" @default.
- W3204752223 modified "2023-09-26" @default.
- W3204752223 title "Multi-Level Curriculum for Training A Distortion-Aware Barrel Distortion Rectification Model" @default.
- W3204752223 cites W1970292545 @default.
- W3204752223 cites W2007347635 @default.
- W3204752223 cites W2021581587 @default.
- W3204752223 cites W2054489417 @default.
- W3204752223 cites W2132653682 @default.
- W3204752223 cites W2148330858 @default.
- W3204752223 cites W2151834591 @default.
- W3204752223 cites W2170196805 @default.
- W3204752223 cites W2296073425 @default.
- W3204752223 cites W2566933398 @default.
- W3204752223 cites W2572730214 @default.
- W3204752223 cites W2732026016 @default.
- W3204752223 cites W2737258237 @default.
- W3204752223 cites W2903345161 @default.
- W3204752223 cites W2913340405 @default.
- W3204752223 cites W2914733350 @default.
- W3204752223 cites W2959131783 @default.
- W3204752223 cites W2979543786 @default.
- W3204752223 cites W2991391304 @default.
- W3204752223 cites W3000169940 @default.
- W3204752223 cites W3016639504 @default.
- W3204752223 doi "https://doi.org/10.1109/iccv48922.2021.00435" @default.
- W3204752223 hasPublicationYear "2021" @default.
- W3204752223 type Work @default.
- W3204752223 sameAs 3204752223 @default.
- W3204752223 citedByCount "4" @default.
- W3204752223 countsByYear W32047522232020 @default.
- W3204752223 countsByYear W32047522232022 @default.
- W3204752223 countsByYear W32047522232023 @default.
- W3204752223 crossrefType "proceedings-article" @default.
- W3204752223 hasAuthorship W3204752223A5028127027 @default.
- W3204752223 hasAuthorship W3204752223A5050402282 @default.
- W3204752223 hasAuthorship W3204752223A5059372830 @default.
- W3204752223 hasAuthorship W3204752223A5069893831 @default.
- W3204752223 hasAuthorship W3204752223A5080547175 @default.
- W3204752223 hasConcept C108583219 @default.
- W3204752223 hasConcept C119599485 @default.
- W3204752223 hasConcept C126780896 @default.
- W3204752223 hasConcept C127413603 @default.
- W3204752223 hasConcept C153180895 @default.
- W3204752223 hasConcept C154945302 @default.
- W3204752223 hasConcept C165801399 @default.
- W3204752223 hasConcept C171614847 @default.
- W3204752223 hasConcept C194257627 @default.
- W3204752223 hasConcept C2776257435 @default.
- W3204752223 hasConcept C31258907 @default.
- W3204752223 hasConcept C41008148 @default.
- W3204752223 hasConcept C41608201 @default.
- W3204752223 hasConcept C50942859 @default.
- W3204752223 hasConceptScore W3204752223C108583219 @default.
- W3204752223 hasConceptScore W3204752223C119599485 @default.
- W3204752223 hasConceptScore W3204752223C126780896 @default.
- W3204752223 hasConceptScore W3204752223C127413603 @default.
- W3204752223 hasConceptScore W3204752223C153180895 @default.
- W3204752223 hasConceptScore W3204752223C154945302 @default.
- W3204752223 hasConceptScore W3204752223C165801399 @default.
- W3204752223 hasConceptScore W3204752223C171614847 @default.
- W3204752223 hasConceptScore W3204752223C194257627 @default.
- W3204752223 hasConceptScore W3204752223C2776257435 @default.
- W3204752223 hasConceptScore W3204752223C31258907 @default.
- W3204752223 hasConceptScore W3204752223C41008148 @default.
- W3204752223 hasConceptScore W3204752223C41608201 @default.
- W3204752223 hasConceptScore W3204752223C50942859 @default.
- W3204752223 hasFunder F4320321001 @default.
- W3204752223 hasLocation W32047522231 @default.
- W3204752223 hasOpenAccess W3204752223 @default.
- W3204752223 hasPrimaryLocation W32047522231 @default.
- W3204752223 hasRelatedWork W1598290781 @default.
- W3204752223 hasRelatedWork W1997267765 @default.
- W3204752223 hasRelatedWork W2352166106 @default.
- W3204752223 hasRelatedWork W2361037395 @default.
- W3204752223 hasRelatedWork W2370721955 @default.
- W3204752223 hasRelatedWork W2392564394 @default.
- W3204752223 hasRelatedWork W2630526526 @default.
- W3204752223 hasRelatedWork W3016639504 @default.
- W3204752223 hasRelatedWork W3082783668 @default.
- W3204752223 hasRelatedWork W4229027300 @default.
- W3204752223 isParatext "false" @default.
- W3204752223 isRetracted "false" @default.
- W3204752223 magId "3204752223" @default.
- W3204752223 workType "article" @default.