FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2949207595> ?p ?o ?g. }

• W2949207595 abstract "Human shape estimation is an important task for video editing, animation and fashion industry. Predicting 3D human body shape from natural images, however, is highly challenging due to factors such as variation in human bodies, clothing and viewpoint. Prior methods addressing this problem typically attempt to fit parametric body models with certain priors on pose and shape. In this work we argue for an alternative representation and propose BodyNet, a neural network for direct inference of volumetric body shape from a single image. BodyNet is an end-to-end trainable network that benefits from (i) a volumetric 3D loss, (ii) a multi-view re-projection loss, and (iii) intermediate supervision of 2D pose, 2D body part segmentation, and 3D pose. Each of them results in performance improvement as demonstrated by our experiments. To evaluate the method, we fit the SMPL model to our network output and show state-of-the-art results on the SURREAL and Unite the People datasets, outperforming recent approaches. Besides achieving state-of-the-art performance, our method also enables volumetric body-part segmentation." @default.
• W2949207595 created "2019-06-27" @default.
• W2949207595 creator A5009299466 @default.
• W2949207595 creator A5024292507 @default.
• W2949207595 creator A5028817790 @default.
• W2949207595 creator A5045217258 @default.
• W2949207595 creator A5053907649 @default.
• W2949207595 creator A5068985412 @default.
• W2949207595 creator A5087781064 @default.
• W2949207595 date "2018-04-13" @default.
• W2949207595 modified "2023-09-23" @default.
• W2949207595 title "BodyNet: Volumetric Inference of 3D Human Body Shapes" @default.
• W2949207595 cites W1943191679 @default.
• W2949207595 cites W1967554269 @default.
• W2949207595 cites W1989191365 @default.
• W2949207595 cites W2054820429 @default.
• W2949207595 cites W2080873731 @default.
• W2949207595 cites W2083461908 @default.
• W2949207595 cites W2101032778 @default.
• W2949207595 cites W2113325037 @default.
• W2949207595 cites W2122633688 @default.
• W2949207595 cites W2134484928 @default.
• W2949207595 cites W2135533529 @default.
• W2949207595 cites W2147800946 @default.
• W2949207595 cites W2155196764 @default.
• W2949207595 cites W2175012183 @default.
• W2949207595 cites W2211722331 @default.
• W2949207595 cites W2255781698 @default.
• W2949207595 cites W2340779594 @default.
• W2949207595 cites W2467838519 @default.
• W2949207595 cites W2483862638 @default.
• W2949207595 cites W2518246072 @default.
• W2949207595 cites W2522527348 @default.
• W2949207595 cites W2523426658 @default.
• W2949207595 cites W2545173102 @default.
• W2949207595 cites W2554247908 @default.
• W2949207595 cites W2556802233 @default.
• W2949207595 cites W2557698284 @default.
• W2949207595 cites W2560609797 @default.
• W2949207595 cites W2560722161 @default.
• W2949207595 cites W2562703451 @default.
• W2949207595 cites W2573098616 @default.
• W2949207595 cites W2585185777 @default.
• W2949207595 cites W2603429625 @default.
• W2949207595 cites W2605243700 @default.
• W2949207595 cites W2611932403 @default.
• W2949207595 cites W2737780766 @default.
• W2949207595 cites W2785694322 @default.
• W2949207595 cites W2786802517 @default.
• W2949207595 cites W2788865504 @default.
• W2949207595 cites W2892165078 @default.
• W2949207595 cites W2949130266 @default.
• W2949207595 cites W2950701417 @default.
• W2949207595 cites W2950762923 @default.
• W2949207595 cites W2950977907 @default.
• W2949207595 cites W2951863354 @default.
• W2949207595 cites W2951940669 @default.
• W2949207595 cites W2952186347 @default.
• W2949207595 cites W2963013806 @default.
• W2949207595 cites W2963355540 @default.
• W2949207595 cites W2963592930 @default.
• W2949207595 cites W2963688992 @default.
• W2949207595 cites W2963995996 @default.
• W2949207595 cites W2964137676 @default.
• W2949207595 cites W2964145484 @default.
• W2949207595 cites W2964194725 @default.
• W2949207595 cites W3104141662 @default.
• W2949207595 hasPublicationYear "2018" @default.
• W2949207595 type Work @default.
• W2949207595 sameAs 2949207595 @default.
• W2949207595 citedByCount "2" @default.
• W2949207595 countsByYear W29492075952019 @default.
• W2949207595 crossrefType "posted-content" @default.
• W2949207595 hasAuthorship W2949207595A5009299466 @default.
• W2949207595 hasAuthorship W2949207595A5024292507 @default.
• W2949207595 hasAuthorship W2949207595A5028817790 @default.
• W2949207595 hasAuthorship W2949207595A5045217258 @default.
• W2949207595 hasAuthorship W2949207595A5053907649 @default.
• W2949207595 hasAuthorship W2949207595A5068985412 @default.
• W2949207595 hasAuthorship W2949207595A5087781064 @default.
• W2949207595 hasConcept C105795698 @default.
• W2949207595 hasConcept C107673813 @default.
• W2949207595 hasConcept C11413529 @default.
• W2949207595 hasConcept C117251300 @default.
• W2949207595 hasConcept C153180895 @default.
• W2949207595 hasConcept C154945302 @default.
• W2949207595 hasConcept C162324750 @default.
• W2949207595 hasConcept C17744445 @default.
• W2949207595 hasConcept C177769412 @default.
• W2949207595 hasConcept C187736073 @default.
• W2949207595 hasConcept C199539241 @default.
• W2949207595 hasConcept C24574437 @default.
• W2949207595 hasConcept C2776214188 @default.
• W2949207595 hasConcept C2776359362 @default.
• W2949207595 hasConcept C2780451532 @default.
• W2949207595 hasConcept C31972630 @default.
• W2949207595 hasConcept C33923547 @default.
• W2949207595 hasConcept C41008148 @default.
• W2949207595 hasConcept C50644808 @default.
• W2949207595 hasConcept C52102323 @default.

• next