FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2606702283> ?p ?o ?g. }

• W2606702283 endingPage "541" @default.
• W2606702283 startingPage "525" @default.
• W2606702283 abstract "Depth from focus (DFF) is one of the classical ill-posed inverse problems in computer vision. Most approaches recover the depth at each pixel based on the focal setting which exhibits maximal sharpness. Yet, it is not obvious how to reliably estimate the sharpness level, particularly in low-textured areas. In this paper, we propose ‘Deep Depth From Focus (DDFF)’ as the first end-to-end learning approach to this problem. One of the main challenges we face is the hunger for data of deep neural networks. In order to obtain a significant amount of focal stacks with corresponding groundtruth depth, we propose to leverage a light-field camera with a co-calibrated RGB-D sensor. This allows us to digitally create focal stacks of varying sizes. Compared to existing benchmarks our dataset is 25 times larger, enabling the use of machine learning for this inverse problem. We compare our results with state-of-the-art DFF methods and we also analyze the effect of several key deep architectural components. These experiments show that our proposed method ‘DDFFNet’ achieves state-of-the-art performance in all scenes, reducing depth error by more than 75% compared to the classical DFF methods." @default.
• W2606702283 created "2017-04-28" @default.
• W2606702283 creator A5003716742 @default.
• W2606702283 creator A5021396825 @default.
• W2606702283 creator A5084499027 @default.
• W2606702283 creator A5087710605 @default.
• W2606702283 creator A5090283032 @default.
• W2606702283 date "2019-01-01" @default.
• W2606702283 modified "2023-10-02" @default.
• W2606702283 title "Deep Depth from Focus" @default.
• W2606702283 cites W1536680647 @default.
• W2606702283 cites W1677182931 @default.
• W2606702283 cites W1745334888 @default.
• W2606702283 cites W1803059841 @default.
• W2606702283 cites W1893585201 @default.
• W2606702283 cites W1903029394 @default.
• W2606702283 cites W1914596733 @default.
• W2606702283 cites W1923779427 @default.
• W2606702283 cites W1965475047 @default.
• W2606702283 cites W2079239242 @default.
• W2606702283 cites W2103328396 @default.
• W2606702283 cites W2104620097 @default.
• W2606702283 cites W2117539524 @default.
• W2606702283 cites W2118273112 @default.
• W2606702283 cites W2128268941 @default.
• W2606702283 cites W2140073401 @default.
• W2606702283 cites W2143050242 @default.
• W2606702283 cites W2143291846 @default.
• W2606702283 cites W2146695255 @default.
• W2606702283 cites W2194775991 @default.
• W2606702283 cites W2200124539 @default.
• W2606702283 cites W2211024058 @default.
• W2606702283 cites W2297633669 @default.
• W2606702283 cites W2300779272 @default.
• W2606702283 cites W2431126524 @default.
• W2606702283 cites W2464308330 @default.
• W2606702283 cites W2560023338 @default.
• W2606702283 cites W2584731199 @default.
• W2606702283 cites W2587989515 @default.
• W2606702283 cites W2591697814 @default.
• W2606702283 cites W2778641202 @default.
• W2606702283 cites W2963881378 @default.
• W2606702283 cites W4244705922 @default.
• W2606702283 cites W764651262 @default.
• W2606702283 doi "https://doi.org/10.1007/978-3-030-20893-6_33" @default.
• W2606702283 hasPublicationYear "2019" @default.
• W2606702283 type Work @default.
• W2606702283 sameAs 2606702283 @default.
• W2606702283 citedByCount "23" @default.
• W2606702283 countsByYear W26067022832019 @default.
• W2606702283 countsByYear W26067022832020 @default.
• W2606702283 countsByYear W26067022832021 @default.
• W2606702283 countsByYear W26067022832022 @default.
• W2606702283 countsByYear W26067022832023 @default.
• W2606702283 crossrefType "book-chapter" @default.
• W2606702283 hasAuthorship W2606702283A5003716742 @default.
• W2606702283 hasAuthorship W2606702283A5021396825 @default.
• W2606702283 hasAuthorship W2606702283A5084499027 @default.
• W2606702283 hasAuthorship W2606702283A5087710605 @default.
• W2606702283 hasAuthorship W2606702283A5090283032 @default.
• W2606702283 hasConcept C108583219 @default.
• W2606702283 hasConcept C11413529 @default.
• W2606702283 hasConcept C115961682 @default.
• W2606702283 hasConcept C120665830 @default.
• W2606702283 hasConcept C121332964 @default.
• W2606702283 hasConcept C141268832 @default.
• W2606702283 hasConcept C144024400 @default.
• W2606702283 hasConcept C153083717 @default.
• W2606702283 hasConcept C15336307 @default.
• W2606702283 hasConcept C154945302 @default.
• W2606702283 hasConcept C183072630 @default.
• W2606702283 hasConcept C192209626 @default.
• W2606702283 hasConcept C202444582 @default.
• W2606702283 hasConcept C207467116 @default.
• W2606702283 hasConcept C2524010 @default.
• W2606702283 hasConcept C2779304628 @default.
• W2606702283 hasConcept C2984842247 @default.
• W2606702283 hasConcept C31972630 @default.
• W2606702283 hasConcept C33923547 @default.
• W2606702283 hasConcept C36289849 @default.
• W2606702283 hasConcept C41008148 @default.
• W2606702283 hasConcept C50644808 @default.
• W2606702283 hasConcept C82552819 @default.
• W2606702283 hasConcept C82990744 @default.
• W2606702283 hasConcept C9652623 @default.
• W2606702283 hasConceptScore W2606702283C108583219 @default.
• W2606702283 hasConceptScore W2606702283C11413529 @default.
• W2606702283 hasConceptScore W2606702283C115961682 @default.
• W2606702283 hasConceptScore W2606702283C120665830 @default.
• W2606702283 hasConceptScore W2606702283C121332964 @default.
• W2606702283 hasConceptScore W2606702283C141268832 @default.
• W2606702283 hasConceptScore W2606702283C144024400 @default.
• W2606702283 hasConceptScore W2606702283C153083717 @default.
• W2606702283 hasConceptScore W2606702283C15336307 @default.
• W2606702283 hasConceptScore W2606702283C154945302 @default.
• W2606702283 hasConceptScore W2606702283C183072630 @default.
• W2606702283 hasConceptScore W2606702283C192209626 @default.
• W2606702283 hasConceptScore W2606702283C202444582 @default.

• next