Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996100614> ?p ?o ?g. }
- W2996100614 abstract "In recent years, Generative Adversarial Networks have achieved impressive results in photorealistic image synthesis. This progress nurtures hopes that one day the classical rendering pipeline can be replaced by efficient models that are learned directly from images. However, current image synthesis models operate in the 2D domain where disentangling 3D properties such as camera viewpoint or object pose is challenging. Furthermore, they lack an interpretable and controllable representation. Our key hypothesis is that the image generation process should be modeled in 3D space as the physical world surrounding us is intrinsically three-dimensional. We define the new task of 3D controllable image synthesis and propose an approach for solving it by reasoning both in 3D space and in the 2D image domain. We demonstrate that our model is able to disentangle latent 3D factors of simple multi-object scenes in an unsupervised fashion from raw images. Compared to pure 2D baselines, it allows for synthesizing scenes that are consistent wrt. changes in viewpoint or object pose. We further evaluate various 3D representations in terms of their usefulness for this challenging task." @default.
- W2996100614 created "2019-12-26" @default.
- W2996100614 creator A5016606943 @default.
- W2996100614 creator A5018811297 @default.
- W2996100614 creator A5028087949 @default.
- W2996100614 creator A5055590646 @default.
- W2996100614 date "2019-12-11" @default.
- W2996100614 modified "2023-09-23" @default.
- W2996100614 title "Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis" @default.
- W2996100614 cites W2099471712 @default.
- W2996100614 cites W2157617585 @default.
- W2996100614 cites W2163922914 @default.
- W2996100614 cites W2173520492 @default.
- W2996100614 cites W2190691619 @default.
- W2996100614 cites W2194775991 @default.
- W2996100614 cites W2298992465 @default.
- W2996100614 cites W2530372461 @default.
- W2996100614 cites W2592101326 @default.
- W2996100614 cites W2619503996 @default.
- W2996100614 cites W2792263949 @default.
- W2996100614 cites W2807242871 @default.
- W2996100614 cites W2889582485 @default.
- W2996100614 cites W2903200123 @default.
- W2996100614 cites W2903538854 @default.
- W2996100614 cites W2911448865 @default.
- W2996100614 cites W2914914077 @default.
- W2996100614 cites W2919112510 @default.
- W2996100614 cites W2929298487 @default.
- W2996100614 cites W2951880955 @default.
- W2996100614 cites W2952484912 @default.
- W2996100614 cites W2952489094 @default.
- W2996100614 cites W2962760235 @default.
- W2996100614 cites W2962770929 @default.
- W2996100614 cites W2962778872 @default.
- W2996100614 cites W2962864875 @default.
- W2996100614 cites W2962889261 @default.
- W2996100614 cites W2963026643 @default.
- W2996100614 cites W2963038612 @default.
- W2996100614 cites W2963073614 @default.
- W2996100614 cites W2963184176 @default.
- W2996100614 cites W2963226019 @default.
- W2996100614 cites W2963370555 @default.
- W2996100614 cites W2963475767 @default.
- W2996100614 cites W2963522749 @default.
- W2996100614 cites W2963527086 @default.
- W2996100614 cites W2963836885 @default.
- W2996100614 cites W2963901923 @default.
- W2996100614 cites W2963951231 @default.
- W2996100614 cites W2963981733 @default.
- W2996100614 cites W2964213104 @default.
- W2996100614 cites W2964846271 @default.
- W2996100614 cites W2965084509 @default.
- W2996100614 cites W2965412140 @default.
- W2996100614 cites W2965833116 @default.
- W2996100614 cites W2969485315 @default.
- W2996100614 cites W2976164226 @default.
- W2996100614 cites W2979308149 @default.
- W2996100614 cites W2982041717 @default.
- W2996100614 cites W2987919422 @default.
- W2996100614 cites W2990173985 @default.
- W2996100614 cites W3008102851 @default.
- W2996100614 doi "https://doi.org/10.48550/arxiv.1912.05237" @default.
- W2996100614 hasPublicationYear "2019" @default.
- W2996100614 type Work @default.
- W2996100614 sameAs 2996100614 @default.
- W2996100614 citedByCount "2" @default.
- W2996100614 countsByYear W29961006142020 @default.
- W2996100614 crossrefType "posted-content" @default.
- W2996100614 hasAuthorship W2996100614A5016606943 @default.
- W2996100614 hasAuthorship W2996100614A5018811297 @default.
- W2996100614 hasAuthorship W2996100614A5028087949 @default.
- W2996100614 hasAuthorship W2996100614A5055590646 @default.
- W2996100614 hasBestOaLocation W29961006141 @default.
- W2996100614 hasConcept C115961682 @default.
- W2996100614 hasConcept C134306372 @default.
- W2996100614 hasConcept C154945302 @default.
- W2996100614 hasConcept C162324750 @default.
- W2996100614 hasConcept C167966045 @default.
- W2996100614 hasConcept C17744445 @default.
- W2996100614 hasConcept C187736073 @default.
- W2996100614 hasConcept C199539241 @default.
- W2996100614 hasConcept C205711294 @default.
- W2996100614 hasConcept C2776359362 @default.
- W2996100614 hasConcept C2776449333 @default.
- W2996100614 hasConcept C2780451532 @default.
- W2996100614 hasConcept C2781238097 @default.
- W2996100614 hasConcept C2989087649 @default.
- W2996100614 hasConcept C31972630 @default.
- W2996100614 hasConcept C33923547 @default.
- W2996100614 hasConcept C36503486 @default.
- W2996100614 hasConcept C39890363 @default.
- W2996100614 hasConcept C41008148 @default.
- W2996100614 hasConcept C59404180 @default.
- W2996100614 hasConcept C94625758 @default.
- W2996100614 hasConceptScore W2996100614C115961682 @default.
- W2996100614 hasConceptScore W2996100614C134306372 @default.
- W2996100614 hasConceptScore W2996100614C154945302 @default.
- W2996100614 hasConceptScore W2996100614C162324750 @default.
- W2996100614 hasConceptScore W2996100614C167966045 @default.
- W2996100614 hasConceptScore W2996100614C17744445 @default.