Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386075992> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4386075992 abstract "Text-guided image generation has progressed rapidly in recent years, inspiring major breakthroughs in text-guided shape generation. Recently, it has been shown that using score distillation, one can successfully text-guide a NeRF model to generate a 3D object. We adapt the score distillation to the publicly available, and computationally efficient, Latent Diffusion Models, which apply the entire diffusion process in a compact latent space of a pretrained autoencoder. As NeRFs operate in image space, a naive solution for guiding them with latent score distillation would require encoding to the latent space at each guidance step. Instead, we propose to bring the NeRF to the latent space, resulting in a Latent-NeRF. Analyzing our Latent-NeRF, we show that while Text-to-3D models can generate impressive results, they are inherently unconstrained and may lack the ability to guide or enforce a specific 3D structure. To assist and direct the 3D generation, we propose to guide our Latent-NeRF using a Sketch-Shape: an abstract geometry that defines the coarse structure of the desired object. Then, we present means to integrate such a constraint directly into a Latent-NeRF. This unique combination of text and shape guidance allows for increased control over the generation process. We also show that latent score distillation can be successfully applied directly on 3D meshes. This allows for generating high-quality textures on a given geometry. Our experiments validate the power of our different forms of guidance and the efficiency of using latent rendering." @default.
- W4386075992 created "2023-08-23" @default.
- W4386075992 creator A5016129501 @default.
- W4386075992 creator A5036688260 @default.
- W4386075992 creator A5072571599 @default.
- W4386075992 creator A5076541595 @default.
- W4386075992 creator A5085386004 @default.
- W4386075992 date "2023-06-01" @default.
- W4386075992 modified "2023-09-27" @default.
- W4386075992 title "Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures" @default.
- W4386075992 cites W2024395588 @default.
- W4386075992 cites W2811052594 @default.
- W4386075992 cites W2962785568 @default.
- W4386075992 cites W2985840885 @default.
- W4386075992 cites W2986615800 @default.
- W4386075992 cites W3166862086 @default.
- W4386075992 cites W3173531806 @default.
- W4386075992 cites W4200150166 @default.
- W4386075992 cites W4214926101 @default.
- W4386075992 cites W4221151978 @default.
- W4386075992 cites W4226494718 @default.
- W4386075992 cites W4286611278 @default.
- W4386075992 cites W4286616176 @default.
- W4386075992 cites W4294959213 @default.
- W4386075992 cites W4312453532 @default.
- W4386075992 cites W4312708649 @default.
- W4386075992 cites W4312971576 @default.
- W4386075992 cites W4313041309 @default.
- W4386075992 doi "https://doi.org/10.1109/cvpr52729.2023.01218" @default.
- W4386075992 hasPublicationYear "2023" @default.
- W4386075992 type Work @default.
- W4386075992 citedByCount "0" @default.
- W4386075992 crossrefType "proceedings-article" @default.
- W4386075992 hasAuthorship W4386075992A5016129501 @default.
- W4386075992 hasAuthorship W4386075992A5036688260 @default.
- W4386075992 hasAuthorship W4386075992A5072571599 @default.
- W4386075992 hasAuthorship W4386075992A5076541595 @default.
- W4386075992 hasAuthorship W4386075992A5085386004 @default.
- W4386075992 hasConcept C101738243 @default.
- W4386075992 hasConcept C108583219 @default.
- W4386075992 hasConcept C111919701 @default.
- W4386075992 hasConcept C121684516 @default.
- W4386075992 hasConcept C153180895 @default.
- W4386075992 hasConcept C154945302 @default.
- W4386075992 hasConcept C31487907 @default.
- W4386075992 hasConcept C31972630 @default.
- W4386075992 hasConcept C41008148 @default.
- W4386075992 hasConcept C98045186 @default.
- W4386075992 hasConceptScore W4386075992C101738243 @default.
- W4386075992 hasConceptScore W4386075992C108583219 @default.
- W4386075992 hasConceptScore W4386075992C111919701 @default.
- W4386075992 hasConceptScore W4386075992C121684516 @default.
- W4386075992 hasConceptScore W4386075992C153180895 @default.
- W4386075992 hasConceptScore W4386075992C154945302 @default.
- W4386075992 hasConceptScore W4386075992C31487907 @default.
- W4386075992 hasConceptScore W4386075992C31972630 @default.
- W4386075992 hasConceptScore W4386075992C41008148 @default.
- W4386075992 hasConceptScore W4386075992C98045186 @default.
- W4386075992 hasFunder F4320322252 @default.
- W4386075992 hasFunder F4320338335 @default.
- W4386075992 hasLocation W43860759921 @default.
- W4386075992 hasOpenAccess W4386075992 @default.
- W4386075992 hasPrimaryLocation W43860759921 @default.
- W4386075992 hasRelatedWork W2292254049 @default.
- W4386075992 hasRelatedWork W2592385986 @default.
- W4386075992 hasRelatedWork W2772780115 @default.
- W4386075992 hasRelatedWork W2897995864 @default.
- W4386075992 hasRelatedWork W2998168123 @default.
- W4386075992 hasRelatedWork W3099179464 @default.
- W4386075992 hasRelatedWork W3172328353 @default.
- W4386075992 hasRelatedWork W4281924768 @default.
- W4386075992 hasRelatedWork W4287995534 @default.
- W4386075992 hasRelatedWork W4309838615 @default.
- W4386075992 isParatext "false" @default.
- W4386075992 isRetracted "false" @default.
- W4386075992 workType "article" @default.