Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897765997> ?p ?o ?g. }
- W2897765997 abstract "We address the highly challenging problem of real-time 3D hand tracking based on a monocular RGB-only sequence. Our tracking method combines a convolutional neural network with a kinematic 3D hand model, such that it generalizes well to unseen data, is robust to occlusions and varying camera viewpoints, and leads to anatomically plausible as well as temporally smooth hand motions. For training our CNN we propose a novel approach for the synthetic generation of training data that is based on a geometrically consistent image-to-image translation network. To be more specific, we use a neural network that translates synthetic images to real images, such that the so-generated images follow the same statistical distribution as real-world hand images. For training this translation network we combine an adversarial loss and a cycle-consistency loss with a geometric consistency loss in order to preserve geometric properties (such as hand pose) during translation. We demonstrate that our hand tracking system outperforms the current state-of-the-art on challenging RGB-only footage." @default.
- W2897765997 created "2018-10-26" @default.
- W2897765997 creator A5009513081 @default.
- W2897765997 creator A5013373065 @default.
- W2897765997 creator A5014973945 @default.
- W2897765997 creator A5020664641 @default.
- W2897765997 creator A5024553204 @default.
- W2897765997 creator A5045111379 @default.
- W2897765997 creator A5072277461 @default.
- W2897765997 date "2018-06-01" @default.
- W2897765997 modified "2023-10-03" @default.
- W2897765997 title "GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB" @default.
- W2897765997 cites W1923747199 @default.
- W2897765997 cites W1952857803 @default.
- W2897765997 cites W1990947293 @default.
- W2897765997 cites W2003810411 @default.
- W2897765997 cites W2023633446 @default.
- W2897765997 cites W2027222744 @default.
- W2897765997 cites W2051296007 @default.
- W2897765997 cites W2057069782 @default.
- W2897765997 cites W2065228210 @default.
- W2897765997 cites W2075156252 @default.
- W2897765997 cites W2093414253 @default.
- W2897765997 cites W2100428290 @default.
- W2897765997 cites W2107655853 @default.
- W2897765997 cites W2110964220 @default.
- W2897765997 cites W2114663654 @default.
- W2897765997 cites W2130267005 @default.
- W2897765997 cites W2135533529 @default.
- W2897765997 cites W2138672819 @default.
- W2897765997 cites W2143641248 @default.
- W2897765997 cites W2153169563 @default.
- W2897765997 cites W2159756630 @default.
- W2897765997 cites W2165272793 @default.
- W2897765997 cites W2194775991 @default.
- W2897765997 cites W2210697964 @default.
- W2897765997 cites W2218414108 @default.
- W2897765997 cites W2219155316 @default.
- W2897765997 cites W2227547437 @default.
- W2897765997 cites W2466332079 @default.
- W2897765997 cites W2469784314 @default.
- W2897765997 cites W2518780600 @default.
- W2897765997 cites W2525184802 @default.
- W2897765997 cites W2543872873 @default.
- W2897765997 cites W2560481159 @default.
- W2897765997 cites W2576289912 @default.
- W2897765997 cites W2593768305 @default.
- W2897765997 cites W2611932403 @default.
- W2897765997 cites W2616442625 @default.
- W2897765997 cites W2777106508 @default.
- W2897765997 cites W2781143029 @default.
- W2897765997 cites W2962793481 @default.
- W2897765997 cites W2962811204 @default.
- W2897765997 cites W2963073614 @default.
- W2897765997 cites W2963377353 @default.
- W2897765997 cites W2963488642 @default.
- W2897765997 cites W2963522749 @default.
- W2897765997 cites W2963577185 @default.
- W2897765997 cites W2963637380 @default.
- W2897765997 cites W2963709863 @default.
- W2897765997 cites W3098312772 @default.
- W2897765997 cites W3105736391 @default.
- W2897765997 cites W3148721422 @default.
- W2897765997 doi "https://doi.org/10.1109/cvpr.2018.00013" @default.
- W2897765997 hasPublicationYear "2018" @default.
- W2897765997 type Work @default.
- W2897765997 sameAs 2897765997 @default.
- W2897765997 citedByCount "396" @default.
- W2897765997 countsByYear W28977659972018 @default.
- W2897765997 countsByYear W28977659972019 @default.
- W2897765997 countsByYear W28977659972020 @default.
- W2897765997 countsByYear W28977659972021 @default.
- W2897765997 countsByYear W28977659972022 @default.
- W2897765997 countsByYear W28977659972023 @default.
- W2897765997 crossrefType "proceedings-article" @default.
- W2897765997 hasAuthorship W2897765997A5009513081 @default.
- W2897765997 hasAuthorship W2897765997A5013373065 @default.
- W2897765997 hasAuthorship W2897765997A5014973945 @default.
- W2897765997 hasAuthorship W2897765997A5020664641 @default.
- W2897765997 hasAuthorship W2897765997A5024553204 @default.
- W2897765997 hasAuthorship W2897765997A5045111379 @default.
- W2897765997 hasAuthorship W2897765997A5072277461 @default.
- W2897765997 hasBestOaLocation W28977659972 @default.
- W2897765997 hasConcept C104317684 @default.
- W2897765997 hasConcept C105580179 @default.
- W2897765997 hasConcept C108583219 @default.
- W2897765997 hasConcept C115961682 @default.
- W2897765997 hasConcept C121332964 @default.
- W2897765997 hasConcept C149364088 @default.
- W2897765997 hasConcept C154945302 @default.
- W2897765997 hasConcept C15744967 @default.
- W2897765997 hasConcept C185592680 @default.
- W2897765997 hasConcept C19417346 @default.
- W2897765997 hasConcept C2775936607 @default.
- W2897765997 hasConcept C2776436953 @default.
- W2897765997 hasConcept C2779757391 @default.
- W2897765997 hasConcept C31972630 @default.
- W2897765997 hasConcept C39920418 @default.
- W2897765997 hasConcept C41008148 @default.
- W2897765997 hasConcept C55493867 @default.