FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377001496> ?p ?o ?g. }

• W4377001496 endingPage "10614" @default.
• W4377001496 startingPage "10603" @default.
• W4377001496 abstract "Image editing and compositing have become ubiquitous in entertainment, from digital art to AR and VR experiences. To produce beautiful composites, the camera needs to be geometrically calibrated, which can be tedious and requires a physical calibration target. In place of the traditional multi-image calibration process, we propose to infer the camera calibration parameters such as pitch, roll, field of view, and lens distortion directly from a single image using a deep convolutional neural network. We train this network using automatically generated samples from a large-scale panorama dataset, yielding competitive accuracy in terms of standard l2 error. However, we argue that minimizing such standard error metrics might not be optimal for many applications. In this work, we investigate human sensitivity to inaccuracies in geometric camera calibration. To this end, we conduct a large-scale human perception study where we ask participants to judge the realism of 3D objects composited with correct and biased camera calibration parameters. Based on this study, we develop a new perceptual measure for camera calibration and demonstrate that our deep calibration network outperforms previous single-image based calibration methods both on standard metrics as well as on this novel perceptual measure. Finally, we demonstrate the use of our calibration network for several applications, including virtual object insertion, image retrieval, and compositing." @default.
• W4377001496 created "2023-05-19" @default.
• W4377001496 creator A5006855516 @default.
• W4377001496 creator A5029086954 @default.
• W4377001496 creator A5032004510 @default.
• W4377001496 creator A5032768302 @default.
• W4377001496 creator A5034761030 @default.
• W4377001496 creator A5090418377 @default.
• W4377001496 date "2023-09-01" @default.
• W4377001496 modified "2023-09-30" @default.
• W4377001496 title "A Perceptual Measure for Deep Single Image Camera and Lens Calibration" @default.
• W4377001496 cites W1481030273 @default.
• W4377001496 cites W1504729745 @default.
• W4377001496 cites W1559849818 @default.
• W4377001496 cites W1592011777 @default.
• W4377001496 cites W1895577753 @default.
• W4377001496 cites W1910129379 @default.
• W4377001496 cites W1977341822 @default.
• W4377001496 cites W2023614206 @default.
• W4377001496 cites W2029450947 @default.
• W4377001496 cites W2032704023 @default.
• W4377001496 cites W2033819227 @default.
• W4377001496 cites W2035837348 @default.
• W4377001496 cites W2039637700 @default.
• W4377001496 cites W2054489417 @default.
• W4377001496 cites W2057766517 @default.
• W4377001496 cites W2061008391 @default.
• W4377001496 cites W2092384585 @default.
• W4377001496 cites W2100893637 @default.
• W4377001496 cites W2103569660 @default.
• W4377001496 cites W2105680090 @default.
• W4377001496 cites W2112634643 @default.
• W4377001496 cites W2112731915 @default.
• W4377001496 cites W2117539524 @default.
• W4377001496 cites W2121972999 @default.
• W4377001496 cites W2132653682 @default.
• W4377001496 cites W2134867446 @default.
• W4377001496 cites W2144042618 @default.
• W4377001496 cites W2146814781 @default.
• W4377001496 cites W2149827010 @default.
• W4377001496 cites W2157641950 @default.
• W4377001496 cites W2164788504 @default.
• W4377001496 cites W2167667767 @default.
• W4377001496 cites W2169796049 @default.
• W4377001496 cites W2294109271 @default.
• W4377001496 cites W2331128040 @default.
• W4377001496 cites W2417041764 @default.
• W4377001496 cites W2471962767 @default.
• W4377001496 cites W2502575609 @default.
• W4377001496 cites W2519683295 @default.
• W4377001496 cites W2534523274 @default.
• W4377001496 cites W2545070390 @default.
• W4377001496 cites W2554856610 @default.
• W4377001496 cites W2605060370 @default.
• W4377001496 cites W2611857613 @default.
• W4377001496 cites W2614034427 @default.
• W4377001496 cites W2732026016 @default.
• W4377001496 cites W2903345161 @default.
• W4377001496 cites W2962785568 @default.
• W4377001496 cites W2962833508 @default.
• W4377001496 cites W2963340594 @default.
• W4377001496 cites W2963404738 @default.
• W4377001496 cites W2963470893 @default.
• W4377001496 cites W2964237243 @default.
• W4377001496 cites W2968098949 @default.
• W4377001496 cites W2981831938 @default.
• W4377001496 cites W3009662750 @default.
• W4377001496 cites W3103662244 @default.
• W4377001496 cites W3120162918 @default.
• W4377001496 cites W3145547920 @default.
• W4377001496 cites W4229523108 @default.
• W4377001496 cites W4229844323 @default.
• W4377001496 cites W4241222664 @default.
• W4377001496 cites W4250490592 @default.
• W4377001496 cites W4250952223 @default.
• W4377001496 cites W569232324 @default.
• W4377001496 doi "https://doi.org/10.1109/tpami.2023.3269641" @default.
• W4377001496 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37195850" @default.
• W4377001496 hasPublicationYear "2023" @default.
• W4377001496 type Work @default.
• W4377001496 citedByCount "0" @default.
• W4377001496 crossrefType "journal-article" @default.
• W4377001496 hasAuthorship W4377001496A5006855516 @default.
• W4377001496 hasAuthorship W4377001496A5029086954 @default.
• W4377001496 hasAuthorship W4377001496A5032004510 @default.
• W4377001496 hasAuthorship W4377001496A5032768302 @default.
• W4377001496 hasAuthorship W4377001496A5034761030 @default.
• W4377001496 hasAuthorship W4377001496A5090418377 @default.
• W4377001496 hasConcept C105795698 @default.
• W4377001496 hasConcept C110898773 @default.
• W4377001496 hasConcept C120665830 @default.
• W4377001496 hasConcept C121332964 @default.
• W4377001496 hasConcept C126780896 @default.
• W4377001496 hasConcept C15336307 @default.
• W4377001496 hasConcept C154945302 @default.
• W4377001496 hasConcept C165838908 @default.
• W4377001496 hasConcept C194257627 @default.
• W4377001496 hasConcept C2776257435 @default.

• next