Matches in SemOpenAlex for { <https://semopenalex.org/work/W2941582463> ?p ?o ?g. }
- W2941582463 abstract "In this work we introduce Lifting Autoencoders, a generative 3D surface-based model of object categories. We bring together ideas from non-rigid structure from motion, image formation, and morphable models to learn a controllable, geometric model of 3D categories in an entirely unsupervised manner from an unstructured set of images. We exploit the 3D geometric nature of our model and use normal information to disentangle appearance into illumination, shading and albedo. We further use weak supervision to disentangle the non-rigid shape variability of human faces into identity and expression. We combine the 3D representation with a differentiable renderer to generate RGB images and append an adversarially trained refinement network to obtain sharp, photorealistic image reconstruction results. The learned generative model can be controlled in terms of interpretable geometry and appearance factors, allowing us to perform photorealistic image manipulation of identity, expression, 3D pose, and illumination properties." @default.
- W2941582463 created "2019-05-03" @default.
- W2941582463 creator A5032864963 @default.
- W2941582463 creator A5034904892 @default.
- W2941582463 creator A5069432184 @default.
- W2941582463 creator A5076307452 @default.
- W2941582463 creator A5077035803 @default.
- W2941582463 creator A5084952250 @default.
- W2941582463 date "2019-04-26" @default.
- W2941582463 modified "2023-10-15" @default.
- W2941582463 title "Lifting AutoEncoders: Unsupervised Learning of a Fully-Disentangled 3D Morphable Model using Deep Non-Rigid Structure from Motion" @default.
- W2941582463 cites W1532217093 @default.
- W2941582463 cites W1834627138 @default.
- W2941582463 cites W1896424170 @default.
- W2941582463 cites W1901129140 @default.
- W2941582463 cites W1925034021 @default.
- W2941582463 cites W1994804971 @default.
- W2941582463 cites W2027560260 @default.
- W2941582463 cites W2033819227 @default.
- W2941582463 cites W2107002953 @default.
- W2941582463 cites W2108428911 @default.
- W2941582463 cites W2110059470 @default.
- W2941582463 cites W2119523460 @default.
- W2941582463 cites W2121299550 @default.
- W2941582463 cites W2121825258 @default.
- W2941582463 cites W2124600577 @default.
- W2941582463 cites W2134724684 @default.
- W2941582463 cites W2136163184 @default.
- W2941582463 cites W2138816964 @default.
- W2941582463 cites W2138835141 @default.
- W2941582463 cites W2160872651 @default.
- W2941582463 cites W2163394682 @default.
- W2941582463 cites W2193045528 @default.
- W2941582463 cites W2203784528 @default.
- W2941582463 cites W2265959009 @default.
- W2941582463 cites W2293657101 @default.
- W2941582463 cites W2301937176 @default.
- W2941582463 cites W2536680313 @default.
- W2941582463 cites W2561074213 @default.
- W2941582463 cites W2576915720 @default.
- W2941582463 cites W2600447016 @default.
- W2941582463 cites W2604524889 @default.
- W2941582463 cites W2607170299 @default.
- W2941582463 cites W2609883120 @default.
- W2941582463 cites W2621394537 @default.
- W2941582463 cites W2767503796 @default.
- W2941582463 cites W2777318693 @default.
- W2941582463 cites W2796822548 @default.
- W2941582463 cites W2798291180 @default.
- W2941582463 cites W2806833697 @default.
- W2941582463 cites W2807725536 @default.
- W2941582463 cites W2884460600 @default.
- W2941582463 cites W2889468636 @default.
- W2941582463 cites W2889887435 @default.
- W2941582463 cites W2890967717 @default.
- W2941582463 cites W2893749619 @default.
- W2941582463 cites W2895439318 @default.
- W2941582463 cites W2899771611 @default.
- W2941582463 cites W2902067433 @default.
- W2941582463 cites W2903206492 @default.
- W2941582463 cites W2903434551 @default.
- W2941582463 cites W2904090037 @default.
- W2941582463 cites W2904367110 @default.
- W2941582463 cites W2906447902 @default.
- W2941582463 cites W2912990735 @default.
- W2941582463 cites W2913581875 @default.
- W2941582463 cites W2915252430 @default.
- W2941582463 cites W2951880955 @default.
- W2941582463 cites W2962760235 @default.
- W2941582463 cites W2962981304 @default.
- W2941582463 cites W2963038612 @default.
- W2941582463 cites W2963073614 @default.
- W2941582463 cites W2963226019 @default.
- W2941582463 cites W2963342110 @default.
- W2941582463 cites W2963370189 @default.
- W2941582463 cites W2963433432 @default.
- W2941582463 cites W2963527086 @default.
- W2941582463 cites W2963604457 @default.
- W2941582463 cites W2963644875 @default.
- W2941582463 cites W2963706553 @default.
- W2941582463 cites W2963730200 @default.
- W2941582463 cites W2963823554 @default.
- W2941582463 cites W2963850211 @default.
- W2941582463 cites W2963888409 @default.
- W2941582463 cites W2964053173 @default.
- W2941582463 cites W2964094607 @default.
- W2941582463 cites W2964121744 @default.
- W2941582463 cites W2991140734 @default.
- W2941582463 cites W3091905774 @default.
- W2941582463 cites W3104792420 @default.
- W2941582463 cites W76980395 @default.
- W2941582463 cites W88425362 @default.
- W2941582463 hasPublicationYear "2019" @default.
- W2941582463 type Work @default.
- W2941582463 sameAs 2941582463 @default.
- W2941582463 citedByCount "2" @default.
- W2941582463 countsByYear W29415824632019 @default.
- W2941582463 countsByYear W29415824632020 @default.
- W2941582463 crossrefType "posted-content" @default.
- W2941582463 hasAuthorship W2941582463A5032864963 @default.