Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288760152> ?p ?o ?g. }
- W4288760152 endingPage "207" @default.
- W4288760152 startingPage "197" @default.
- W4288760152 abstract "Most existing image inpainting methods have achieved remarkable progress in repairing small image defects. However, when the holes are large, their filling contents suffer from structural distortion and center blur due to the weak correlation between known and unknown pixels. In this paper, we propose a Progressive Feature Generation (PFG) network which is mask awareable during the process of filling irregular holes. Specifically, in order to strengthen the constraint for the hole center, we propose dynamic partial convolution which can adaptively adjust the inpainting proportion according to mask ratio in each recurrence. To synthesize high-quality features in the feature generation phase, two parallel encoders are designed which could effectively improve the capability of model to restore large holes. We argue that during feature merging, the signals generated earlier at the same location are more credible. To this end, we develop the sub-regional weighted merging(SWM) method for PFG-Net to accurately merge the feature maps generated during the whole reconstruction process. Experiments on CelebA, Places2, and Paris StreetView datasets show that our model has excellent performance especially for large holes." @default.
- W4288760152 created "2022-07-30" @default.
- W4288760152 creator A5010465278 @default.
- W4288760152 creator A5013878126 @default.
- W4288760152 creator A5044026816 @default.
- W4288760152 creator A5046082807 @default.
- W4288760152 creator A5070538645 @default.
- W4288760152 date "2022-10-01" @default.
- W4288760152 modified "2023-10-16" @default.
- W4288760152 title "Progressive feature generation with mask awareness for image inpainting" @default.
- W4288760152 cites W1834627138 @default.
- W4288760152 cites W1993120651 @default.
- W4288760152 cites W2055132753 @default.
- W4288760152 cites W2064675550 @default.
- W4288760152 cites W2105038642 @default.
- W4288760152 cites W2164490837 @default.
- W4288760152 cites W2295936755 @default.
- W4288760152 cites W2463205272 @default.
- W4288760152 cites W2557414982 @default.
- W4288760152 cites W2732026016 @default.
- W4288760152 cites W2738588019 @default.
- W4288760152 cites W2798365772 @default.
- W4288760152 cites W2891485065 @default.
- W4288760152 cites W2896434438 @default.
- W4288760152 cites W2901084129 @default.
- W4288760152 cites W2963231084 @default.
- W4288760152 cites W2963270367 @default.
- W4288760152 cites W2963420272 @default.
- W4288760152 cites W2963917315 @default.
- W4288760152 cites W2964148878 @default.
- W4288760152 cites W2981682056 @default.
- W4288760152 cites W2982763192 @default.
- W4288760152 cites W2985764327 @default.
- W4288760152 cites W2989207674 @default.
- W4288760152 cites W2990886896 @default.
- W4288760152 cites W2991377405 @default.
- W4288760152 cites W2997669187 @default.
- W4288760152 cites W3034419329 @default.
- W4288760152 cites W3034482833 @default.
- W4288760152 cites W3034814868 @default.
- W4288760152 cites W3035512475 @default.
- W4288760152 cites W3043547428 @default.
- W4288760152 cites W3100903158 @default.
- W4288760152 cites W3111738934 @default.
- W4288760152 cites W3158999687 @default.
- W4288760152 cites W3166762869 @default.
- W4288760152 cites W3171933509 @default.
- W4288760152 cites W3175375202 @default.
- W4288760152 cites W3199003182 @default.
- W4288760152 cites W3204170321 @default.
- W4288760152 cites W373972560 @default.
- W4288760152 doi "https://doi.org/10.1016/j.cag.2022.07.022" @default.
- W4288760152 hasPublicationYear "2022" @default.
- W4288760152 type Work @default.
- W4288760152 citedByCount "1" @default.
- W4288760152 countsByYear W42887601522022 @default.
- W4288760152 crossrefType "journal-article" @default.
- W4288760152 hasAuthorship W4288760152A5010465278 @default.
- W4288760152 hasAuthorship W4288760152A5013878126 @default.
- W4288760152 hasAuthorship W4288760152A5044026816 @default.
- W4288760152 hasAuthorship W4288760152A5046082807 @default.
- W4288760152 hasAuthorship W4288760152A5070538645 @default.
- W4288760152 hasConcept C111919701 @default.
- W4288760152 hasConcept C115961682 @default.
- W4288760152 hasConcept C11727466 @default.
- W4288760152 hasConcept C118505674 @default.
- W4288760152 hasConcept C126780896 @default.
- W4288760152 hasConcept C138885662 @default.
- W4288760152 hasConcept C153180895 @default.
- W4288760152 hasConcept C154945302 @default.
- W4288760152 hasConcept C160633673 @default.
- W4288760152 hasConcept C194257627 @default.
- W4288760152 hasConcept C197129107 @default.
- W4288760152 hasConcept C23123220 @default.
- W4288760152 hasConcept C2776257435 @default.
- W4288760152 hasConcept C2776401178 @default.
- W4288760152 hasConcept C31258907 @default.
- W4288760152 hasConcept C31972630 @default.
- W4288760152 hasConcept C41008148 @default.
- W4288760152 hasConcept C41895202 @default.
- W4288760152 hasConcept C45347329 @default.
- W4288760152 hasConcept C50644808 @default.
- W4288760152 hasConcept C98045186 @default.
- W4288760152 hasConceptScore W4288760152C111919701 @default.
- W4288760152 hasConceptScore W4288760152C115961682 @default.
- W4288760152 hasConceptScore W4288760152C11727466 @default.
- W4288760152 hasConceptScore W4288760152C118505674 @default.
- W4288760152 hasConceptScore W4288760152C126780896 @default.
- W4288760152 hasConceptScore W4288760152C138885662 @default.
- W4288760152 hasConceptScore W4288760152C153180895 @default.
- W4288760152 hasConceptScore W4288760152C154945302 @default.
- W4288760152 hasConceptScore W4288760152C160633673 @default.
- W4288760152 hasConceptScore W4288760152C194257627 @default.
- W4288760152 hasConceptScore W4288760152C197129107 @default.
- W4288760152 hasConceptScore W4288760152C23123220 @default.
- W4288760152 hasConceptScore W4288760152C2776257435 @default.
- W4288760152 hasConceptScore W4288760152C2776401178 @default.
- W4288760152 hasConceptScore W4288760152C31258907 @default.