FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2970670192> ?p ?o ?g. }

• W2970670192 endingPage "97" @default.
• W2970670192 startingPage "83" @default.
• W2970670192 abstract "We present a learning-based approach to reconstructing high-resolution three-dimensional (3D) shapes with detailed geometry and high-fidelity textures. Albeit extensively studied, algorithms for 3D reconstruction from multi-view depth-and-color (RGB-D) scans are still prone to measurement noise and occlusions; limited scanning or capturing angles also often lead to incomplete reconstructions. Propelled by recent advances in 3D deep learning techniques, in this paper, we introduce a novel computation- and memory-efficient cascaded 3D convolutional network architecture, which learns to reconstruct implicit surface representations as well as the corresponding color information from noisy and imperfect RGB-D maps. The proposed 3D neural network performs reconstruction in a progressive and coarse-to-fine manner, achieving unprecedented output resolution and fidelity. Meanwhile, an algorithm for end-to-end training of the proposed cascaded structure is developed. We further introduce Human10, a newly created dataset containing both detailed and textured full-body reconstructions as well as corresponding raw RGB-D scans of 10 subjects. Qualitative and quantitative experimental results on both synthetic and real-world datasets demonstrate that the presented approach outperforms existing state-of-the-art work regarding visual quality and accuracy of reconstructed models." @default.
• W2970670192 created "2019-09-05" @default.
• W2970670192 creator A5013917396 @default.
• W2970670192 creator A5019712537 @default.
• W2970670192 creator A5036300670 @default.
• W2970670192 creator A5037233582 @default.
• W2970670192 creator A5091525681 @default.
• W2970670192 date "2021-01-01" @default.
• W2970670192 modified "2023-10-11" @default.
• W2970670192 title "High-Quality Textured 3D Shape Reconstruction with Cascaded Fully Convolutional Networks" @default.
• W2970670192 cites W1525571356 @default.
• W2970670192 cites W1545706943 @default.
• W2970670192 cites W1565245011 @default.
• W2970670192 cites W1964057156 @default.
• W2970670192 cites W1967554269 @default.
• W2970670192 cites W1971719398 @default.
• W2970670192 cites W1975636777 @default.
• W2970670192 cites W1977758817 @default.
• W2970670192 cites W1979061520 @default.
• W2970670192 cites W1983553998 @default.
• W2970670192 cites W1987648924 @default.
• W2970670192 cites W1992642990 @default.
• W2970670192 cites W2004402003 @default.
• W2970670192 cites W2007417549 @default.
• W2970670192 cites W2009422376 @default.
• W2970670192 cites W2021930164 @default.
• W2970670192 cites W2039594111 @default.
• W2970670192 cites W2044618760 @default.
• W2970670192 cites W2049351243 @default.
• W2970670192 cites W2053825465 @default.
• W2970670192 cites W2057316718 @default.
• W2970670192 cites W2065906272 @default.
• W2970670192 cites W2068337491 @default.
• W2970670192 cites W2071906076 @default.
• W2970670192 cites W2077263423 @default.
• W2970670192 cites W2091226544 @default.
• W2970670192 cites W2091297047 @default.
• W2970670192 cites W2140950877 @default.
• W2970670192 cites W2163827099 @default.
• W2970670192 cites W2167335287 @default.
• W2970670192 cites W2168545424 @default.
• W2970670192 cites W2238402354 @default.
• W2970670192 cites W2250172176 @default.
• W2970670192 cites W2294985758 @default.
• W2970670192 cites W2338532005 @default.
• W2970670192 cites W2342277278 @default.
• W2970670192 cites W2345333930 @default.
• W2970670192 cites W2348664362 @default.
• W2970670192 cites W2366389387 @default.
• W2970670192 cites W2412782625 @default.
• W2970670192 cites W2444097022 @default.
• W2970670192 cites W2495603374 @default.
• W2970670192 cites W2520105578 @default.
• W2970670192 cites W2527142681 @default.
• W2970670192 cites W2532511219 @default.
• W2970670192 cites W2554759989 @default.
• W2970670192 cites W2556802233 @default.
• W2970670192 cites W2557465155 @default.
• W2970670192 cites W2559882727 @default.
• W2970670192 cites W2560609797 @default.
• W2970670192 cites W2598591334 @default.
• W2970670192 cites W2603429625 @default.
• W2970670192 cites W2604493845 @default.
• W2970670192 cites W2609754928 @default.
• W2970670192 cites W2613041730 @default.
• W2970670192 cites W2738588019 @default.
• W2970670192 cites W2751274923 @default.
• W2970670192 cites W2793768642 @default.
• W2970670192 cites W2797515701 @default.
• W2970670192 cites W2802758546 @default.
• W2970670192 cites W2811169695 @default.
• W2970670192 cites W2894865236 @default.
• W2970670192 cites W2895524927 @default.
• W2970670192 cites W2901584762 @default.
• W2970670192 cites W2901982540 @default.
• W2970670192 cites W2963622297 @default.
• W2970670192 cites W2963648573 @default.
• W2970670192 cites W2963735494 @default.
• W2970670192 cites W2963739349 @default.
• W2970670192 cites W2963995996 @default.
• W2970670192 cites W2997095758 @default.
• W2970670192 cites W3000211808 @default.
• W2970670192 cites W3002795340 @default.
• W2970670192 cites W3102132650 @default.
• W2970670192 cites W3104141662 @default.
• W2970670192 cites W3137369665 @default.
• W2970670192 cites W4233857083 @default.
• W2970670192 cites W4249710618 @default.
• W2970670192 cites W4252201060 @default.
• W2970670192 cites W4255872157 @default.
• W2970670192 doi "https://doi.org/10.1109/tvcg.2019.2937300" @default.
• W2970670192 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31449026" @default.
• W2970670192 hasPublicationYear "2021" @default.
• W2970670192 type Work @default.
• W2970670192 sameAs 2970670192 @default.
• W2970670192 citedByCount "14" @default.
• W2970670192 countsByYear W29706701922021 @default.
• W2970670192 countsByYear W29706701922022 @default.

• next