FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2994712368> ?p ?o ?g. }

• W2994712368 abstract "Finding point-wise correspondences between images is a long-standing problem in image analysis. This becomes particularly challenging for sketch images, due to the varying nature of human drawing style, projection distortions and viewport changes. In this paper we present the first attempt to obtain a learned descriptor for dense registration in line drawings. Based on recent deep learning techniques for corresponding photographs, we designed descriptors to locally match image pairs where the object of interest belongs to the same semantic category, yet still differ drastically in shape, form, and projection angle. To this end, we have specifically crafted a data set of synthetic sketches using non-photorealistic rendering over a large collection of part-based registered 3D models. After training, a neural network generates descriptors for every pixel in an input image, which are shown to generalize correctly in unseen sketches hand-drawn by humans. We evaluate our method against a baseline of correspondences data collected from expert designers, in addition to comparisons with other descriptors that have been proven effective in sketches. Code, data and further resources will be publicly released by the time of publication." @default.
• W2994712368 created "2019-12-26" @default.
• W2994712368 creator A5006734638 @default.
• W2994712368 creator A5007211221 @default.
• W2994712368 creator A5054255365 @default.
• W2994712368 creator A5058156675 @default.
• W2994712368 date "2019-11-29" @default.
• W2994712368 modified "2023-09-23" @default.
• W2994712368 title "SketchZooms: Deep multi-view descriptors for matching line drawings" @default.
• W2994712368 cites W1686810756 @default.
• W2994712368 cites W1869500417 @default.
• W2994712368 cites W1892078565 @default.
• W2994712368 cites W1926639317 @default.
• W2994712368 cites W1929856797 @default.
• W2994712368 cites W1955055330 @default.
• W2994712368 cites W1972420097 @default.
• W2994712368 cites W1981220214 @default.
• W2994712368 cites W1985664898 @default.
• W2994712368 cites W1996135899 @default.
• W2994712368 cites W1997196309 @default.
• W2994712368 cites W2003745532 @default.
• W2994712368 cites W2014541013 @default.
• W2994712368 cites W2017606563 @default.
• W2994712368 cites W2026019603 @default.
• W2994712368 cites W2026996548 @default.
• W2994712368 cites W2031760064 @default.
• W2994712368 cites W2036602712 @default.
• W2994712368 cites W2048060845 @default.
• W2994712368 cites W2055678567 @default.
• W2994712368 cites W2057175746 @default.
• W2994712368 cites W2062118960 @default.
• W2994712368 cites W2072905181 @default.
• W2994712368 cites W2074346721 @default.
• W2994712368 cites W2081737438 @default.
• W2994712368 cites W2124386111 @default.
• W2994712368 cites W2127934090 @default.
• W2994712368 cites W2130103520 @default.
• W2994712368 cites W2140033798 @default.
• W2994712368 cites W2154663802 @default.
• W2994712368 cites W2183589061 @default.
• W2994712368 cites W2194775991 @default.
• W2994712368 cites W2222512263 @default.
• W2994712368 cites W2228002889 @default.
• W2994712368 cites W2466618734 @default.
• W2994712368 cites W2471581439 @default.
• W2994712368 cites W2474531669 @default.
• W2994712368 cites W2474574787 @default.
• W2994712368 cites W2501192503 @default.
• W2994712368 cites W2511925527 @default.
• W2994712368 cites W2529895177 @default.
• W2994712368 cites W2553307952 @default.
• W2994712368 cites W2553913815 @default.
• W2994712368 cites W2566812041 @default.
• W2994712368 cites W2588255158 @default.
• W2994712368 cites W2593948489 @default.
• W2994712368 cites W2604662340 @default.
• W2994712368 cites W2606712314 @default.
• W2994712368 cites W2685669664 @default.
• W2994712368 cites W2737260104 @default.
• W2994712368 cites W2739245956 @default.
• W2994712368 cites W2752996268 @default.
• W2994712368 cites W2776402438 @default.
• W2994712368 cites W2811499654 @default.
• W2994712368 cites W2896901907 @default.
• W2994712368 cites W2963325280 @default.
• W2994712368 cites W2963350250 @default.
• W2994712368 cites W2963713828 @default.
• W2994712368 cites W2964121744 @default.
• W2994712368 cites W2972900692 @default.
• W2994712368 cites W3006300890 @default.
• W2994712368 cites W3025009576 @default.
• W2994712368 cites W3087797123 @default.
• W2994712368 cites W3123509264 @default.
• W2994712368 cites W2435623039 @default.
• W2994712368 hasPublicationYear "2019" @default.
• W2994712368 type Work @default.
• W2994712368 sameAs 2994712368 @default.
• W2994712368 citedByCount "0" @default.
• W2994712368 crossrefType "posted-content" @default.
• W2994712368 hasAuthorship W2994712368A5006734638 @default.
• W2994712368 hasAuthorship W2994712368A5007211221 @default.
• W2994712368 hasAuthorship W2994712368A5054255365 @default.
• W2994712368 hasAuthorship W2994712368A5058156675 @default.
• W2994712368 hasConcept C105795698 @default.
• W2994712368 hasConcept C11413529 @default.
• W2994712368 hasConcept C121684516 @default.
• W2994712368 hasConcept C127413603 @default.
• W2994712368 hasConcept C154945302 @default.
• W2994712368 hasConcept C165064840 @default.
• W2994712368 hasConcept C177264268 @default.
• W2994712368 hasConcept C199360897 @default.
• W2994712368 hasConcept C199639397 @default.
• W2994712368 hasConcept C205711294 @default.
• W2994712368 hasConcept C2524010 @default.
• W2994712368 hasConcept C2778090530 @default.
• W2994712368 hasConcept C2779231336 @default.
• W2994712368 hasConcept C28719098 @default.
• W2994712368 hasConcept C2983864324 @default.
• W2994712368 hasConcept C31972630 @default.
• W2994712368 hasConcept C33923547 @default.

• next