Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203683983> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W3203683983 abstract "This work addresses the problem of discovering, in an unsupervised manner, interpretable paths in the latent space of pretrained GANs, so as to provide an intuitive and easy way of controlling the underlying generative factors. In doing so, it addresses some of the limitations of the state-of-the-art works, namely, a) that they discover directions that are independent of the latent code, i.e., paths that are linear, and b) that their evaluation relies either on visual inspection or on laborious human labeling. More specifically, we propose to learn non-linear warpings on the latent space, each one parametrized by a set of RBF-based latent space warping functions, and where each warping gives rise to a family of non-linear paths via the gradient of the function. Building on the work of Voynov and Babenko, that discovers linear paths, we optimize the trainable parameters of the set of RBFs, so as that images that are generated by codes along different paths, are easily distinguishable by a discriminator network. This leads to easily distinguishable image transformations, such as pose and facial expressions in facial images. We show that linear paths can be derived as a special case of our method, and show experimentally that non-linear paths in the latent space lead to steeper, more disentangled and interpretable changes in the image space than in state-of-the art methods, both qualitatively and quantitatively. We make the code and the pretrained models publicly available at: this https URL." @default.
- W3203683983 created "2021-10-11" @default.
- W3203683983 creator A5024224610 @default.
- W3203683983 creator A5031205865 @default.
- W3203683983 creator A5089816358 @default.
- W3203683983 date "2021-10-05" @default.
- W3203683983 modified "2023-09-23" @default.
- W3203683983 title "WarpedGANSpace: Finding non-linear RBF paths in GAN latent space" @default.
- W3203683983 cites W1834627138 @default.
- W3203683983 cites W2099471712 @default.
- W3203683983 cites W2108598243 @default.
- W3203683983 cites W2112796928 @default.
- W3203683983 cites W2163922914 @default.
- W3203683983 cites W2194775991 @default.
- W3203683983 cites W2753738274 @default.
- W3203683983 cites W2893749619 @default.
- W3203683983 cites W2903227570 @default.
- W3203683983 cites W2950113871 @default.
- W3203683983 cites W2962760235 @default.
- W3203683983 cites W2962770929 @default.
- W3203683983 cites W2963226019 @default.
- W3203683983 cites W2963307811 @default.
- W3203683983 cites W2963684088 @default.
- W3203683983 cites W2963836885 @default.
- W3203683983 cites W2964074081 @default.
- W3203683983 cites W2964118024 @default.
- W3203683983 cites W2965392395 @default.
- W3203683983 cites W2967013449 @default.
- W3203683983 cites W2969985801 @default.
- W3203683983 cites W2995497846 @default.
- W3203683983 cites W2995801453 @default.
- W3203683983 cites W2996582215 @default.
- W3203683983 cites W2997473052 @default.
- W3203683983 cites W2999811719 @default.
- W3203683983 cites W3003162010 @default.
- W3203683983 cites W3014852036 @default.
- W3203683983 cites W3034431451 @default.
- W3203683983 cites W3034526383 @default.
- W3203683983 cites W3035574324 @default.
- W3203683983 cites W3091560455 @default.
- W3203683983 cites W3125500671 @default.
- W3203683983 cites W3127419657 @default.
- W3203683983 doi "https://doi.org/10.5281/zenodo.5550474" @default.
- W3203683983 hasPublicationYear "2021" @default.
- W3203683983 type Work @default.
- W3203683983 sameAs 3203683983 @default.
- W3203683983 citedByCount "0" @default.
- W3203683983 crossrefType "proceedings" @default.
- W3203683983 hasAuthorship W3203683983A5024224610 @default.
- W3203683983 hasAuthorship W3203683983A5031205865 @default.
- W3203683983 hasAuthorship W3203683983A5089816358 @default.
- W3203683983 hasBestOaLocation W32036839831 @default.
- W3203683983 hasConcept C111919701 @default.
- W3203683983 hasConcept C192562407 @default.
- W3203683983 hasConcept C2778572836 @default.
- W3203683983 hasConcept C41008148 @default.
- W3203683983 hasConceptScore W3203683983C111919701 @default.
- W3203683983 hasConceptScore W3203683983C192562407 @default.
- W3203683983 hasConceptScore W3203683983C2778572836 @default.
- W3203683983 hasConceptScore W3203683983C41008148 @default.
- W3203683983 hasLocation W32036839831 @default.
- W3203683983 hasLocation W32036839832 @default.
- W3203683983 hasLocation W32036839833 @default.
- W3203683983 hasOpenAccess W3203683983 @default.
- W3203683983 hasPrimaryLocation W32036839831 @default.
- W3203683983 hasRelatedWork W2018879842 @default.
- W3203683983 hasRelatedWork W2737498735 @default.
- W3203683983 hasRelatedWork W2744391499 @default.
- W3203683983 hasRelatedWork W2748952813 @default.
- W3203683983 hasRelatedWork W2898370298 @default.
- W3203683983 hasRelatedWork W2899084033 @default.
- W3203683983 hasRelatedWork W3041790586 @default.
- W3203683983 hasRelatedWork W3120461830 @default.
- W3203683983 hasRelatedWork W3144504424 @default.
- W3203683983 hasRelatedWork W4292492973 @default.
- W3203683983 isParatext "false" @default.
- W3203683983 isRetracted "false" @default.
- W3203683983 magId "3203683983" @default.
- W3203683983 workType "paratext" @default.