Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312364013> ?p ?o ?g. }
- W4312364013 endingPage "614" @default.
- W4312364013 startingPage "597" @default.
- W4312364013 abstract "We propose an unsupervised method for 3D geometry-aware representation learning of articulated objects, in which no image-pose pairs or foreground masks are used for training. Though photorealistic images of articulated objects can be rendered with explicit pose control through existing 3D neural representations, these methods require ground truth 3D pose and foreground masks for training, which are expensive to obtain. We obviate this need by learning the representations with GAN training. The generator is trained to produce realistic images of articulated objects from random poses and latent vectors by adversarial training. To avoid a high computational cost for GAN training, we propose an efficient neural representation for articulated objects based on tri-planes and then present a GAN-based framework for its unsupervised training. Experiments demonstrate the efficiency of our method and show that GAN-based training enables the learning of controllable 3D representations without paired supervision." @default.
- W4312364013 created "2023-01-04" @default.
- W4312364013 creator A5025114648 @default.
- W4312364013 creator A5042711470 @default.
- W4312364013 creator A5055735779 @default.
- W4312364013 creator A5088062069 @default.
- W4312364013 date "2022-01-01" @default.
- W4312364013 modified "2023-10-17" @default.
- W4312364013 title "Unsupervised Learning of Efficient Geometry-Aware Neural Articulated Representations" @default.
- W4312364013 cites W1861492603 @default.
- W4312364013 cites W1967554269 @default.
- W4312364013 cites W1992019563 @default.
- W4312364013 cites W1993962870 @default.
- W4312364013 cites W2052728883 @default.
- W4312364013 cites W2080873731 @default.
- W4312364013 cites W2133665775 @default.
- W4312364013 cites W2194775991 @default.
- W4312364013 cites W2215643317 @default.
- W4312364013 cites W2555859288 @default.
- W4312364013 cites W2576289912 @default.
- W4312364013 cites W2582734987 @default.
- W4312364013 cites W2887358179 @default.
- W4312364013 cites W2933283236 @default.
- W4312364013 cites W2946584893 @default.
- W4312364013 cites W2962770929 @default.
- W4312364013 cites W2962785568 @default.
- W4312364013 cites W2962849139 @default.
- W4312364013 cites W2962963674 @default.
- W4312364013 cites W2963627347 @default.
- W4312364013 cites W2963926543 @default.
- W4312364013 cites W2964218552 @default.
- W4312364013 cites W2978956737 @default.
- W4312364013 cites W2984529706 @default.
- W4312364013 cites W3008102851 @default.
- W4312364013 cites W3035574324 @default.
- W4312364013 cites W3107384982 @default.
- W4312364013 cites W3107471220 @default.
- W4312364013 cites W3109585842 @default.
- W4312364013 cites W3136656704 @default.
- W4312364013 cites W3153220274 @default.
- W4312364013 cites W3161462225 @default.
- W4312364013 cites W3173531806 @default.
- W4312364013 cites W3174752334 @default.
- W4312364013 cites W3176179930 @default.
- W4312364013 cites W3176327543 @default.
- W4312364013 cites W3176568184 @default.
- W4312364013 cites W3176625410 @default.
- W4312364013 cites W3202366118 @default.
- W4312364013 cites W3202627061 @default.
- W4312364013 cites W3202804820 @default.
- W4312364013 cites W3203570626 @default.
- W4312364013 cites W3204221554 @default.
- W4312364013 cites W3204654630 @default.
- W4312364013 cites W4200502498 @default.
- W4312364013 cites W4214625585 @default.
- W4312364013 cites W4214661523 @default.
- W4312364013 cites W4214731463 @default.
- W4312364013 cites W4221151978 @default.
- W4312364013 cites W4312325284 @default.
- W4312364013 cites W4312391718 @default.
- W4312364013 cites W4312435448 @default.
- W4312364013 cites W4312453532 @default.
- W4312364013 cites W4312982790 @default.
- W4312364013 doi "https://doi.org/10.1007/978-3-031-19790-1_36" @default.
- W4312364013 hasPublicationYear "2022" @default.
- W4312364013 type Work @default.
- W4312364013 citedByCount "5" @default.
- W4312364013 countsByYear W43123640132022 @default.
- W4312364013 countsByYear W43123640132023 @default.
- W4312364013 crossrefType "book-chapter" @default.
- W4312364013 hasAuthorship W4312364013A5025114648 @default.
- W4312364013 hasAuthorship W4312364013A5042711470 @default.
- W4312364013 hasAuthorship W4312364013A5055735779 @default.
- W4312364013 hasAuthorship W4312364013A5088062069 @default.
- W4312364013 hasBestOaLocation W43123640132 @default.
- W4312364013 hasConcept C115961682 @default.
- W4312364013 hasConcept C121332964 @default.
- W4312364013 hasConcept C146849305 @default.
- W4312364013 hasConcept C153180895 @default.
- W4312364013 hasConcept C153294291 @default.
- W4312364013 hasConcept C154945302 @default.
- W4312364013 hasConcept C163258240 @default.
- W4312364013 hasConcept C17744445 @default.
- W4312364013 hasConcept C199539241 @default.
- W4312364013 hasConcept C2776359362 @default.
- W4312364013 hasConcept C2777211547 @default.
- W4312364013 hasConcept C2780992000 @default.
- W4312364013 hasConcept C31972630 @default.
- W4312364013 hasConcept C41008148 @default.
- W4312364013 hasConcept C62520636 @default.
- W4312364013 hasConcept C8038995 @default.
- W4312364013 hasConcept C94625758 @default.
- W4312364013 hasConceptScore W4312364013C115961682 @default.
- W4312364013 hasConceptScore W4312364013C121332964 @default.
- W4312364013 hasConceptScore W4312364013C146849305 @default.
- W4312364013 hasConceptScore W4312364013C153180895 @default.
- W4312364013 hasConceptScore W4312364013C153294291 @default.
- W4312364013 hasConceptScore W4312364013C154945302 @default.