FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3149192734> ?p ?o ?g. }

• W3149192734 abstract "Tremendous progress in deep generative models has led to photorealistic image synthesis. While achieving compelling results, most approaches operate in the two-dimensional image domain, ignoring the three-dimensional nature of our world. Several recent works therefore propose generative models which are 3D-aware, i.e., scenes are modeled in 3D and then rendered differentiably to the image plane. This leads to impressive 3D consistency, but incorporating such a bias comes at a price: the camera needs to be modeled as well. Current approaches assume fixed intrinsics and a predefined prior over camera pose ranges. As a result, parameter tuning is typically required for real-world data, and results degrade if the data distribution is not matched. Our key hypothesis is that learning a camera generator jointly with the image generator leads to a more principled approach to 3D-aware image synthesis. Further, we propose to decompose the scene into a background and foreground model, leading to more efficient and disentangled scene representations. While training from raw, unposed image collections, we learn a 3D- and camera-aware generative model which faithfully recovers not only the image but also the camera data distribution. At test time, our model generates images with explicit control over the camera as well as the shape and appearance of the scene." @default.
• W3149192734 created "2021-04-13" @default.
• W3149192734 creator A5016606943 @default.
• W3149192734 creator A5088795883 @default.
• W3149192734 date "2021-03-31" @default.
• W3149192734 modified "2023-09-23" @default.
• W3149192734 title "CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields" @default.
• W3149192734 cites W1959608418 @default.
• W3149192734 cites W2026058811 @default.
• W3149192734 cites W2099471712 @default.
• W3149192734 cites W2130840066 @default.
• W3149192734 cites W2157617585 @default.
• W3149192734 cites W2190424233 @default.
• W3149192734 cites W2194775991 @default.
• W3149192734 cites W2298992465 @default.
• W3149192734 cites W2476099471 @default.
• W3149192734 cites W2546066744 @default.
• W3149192734 cites W2582734987 @default.
• W3149192734 cites W2792263949 @default.
• W3149192734 cites W2889582485 @default.
• W3149192734 cites W2893749619 @default.
• W3149192734 cites W2951880955 @default.
• W3149192734 cites W2962760235 @default.
• W3149192734 cites W2962770929 @default.
• W3149192734 cites W2962849139 @default.
• W3149192734 cites W2963038612 @default.
• W3149192734 cites W2963108253 @default.
• W3149192734 cites W2963226019 @default.
• W3149192734 cites W2963623257 @default.
• W3149192734 cites W2963627347 @default.
• W3149192734 cites W2963730200 @default.
• W3149192734 cites W2963767194 @default.
• W3149192734 cites W2963783084 @default.
• W3149192734 cites W2963901923 @default.
• W3149192734 cites W2963926543 @default.
• W3149192734 cites W2969485315 @default.
• W3149192734 cites W2970936521 @default.
• W3149192734 cites W2971278627 @default.
• W3149192734 cites W2976023236 @default.
• W3149192734 cites W2981081013 @default.
• W3149192734 cites W2981657250 @default.
• W3149192734 cites W2981978060 @default.
• W3149192734 cites W2984210651 @default.
• W3149192734 cites W2989630530 @default.
• W3149192734 cites W2989673842 @default.
• W3149192734 cites W2990974996 @default.
• W3149192734 cites W2995801453 @default.
• W3149192734 cites W3003162010 @default.
• W3149192734 cites W3008102851 @default.
• W3149192734 cites W3008490294 @default.
• W3149192734 cites W3014852036 @default.
• W3149192734 cites W3034259269 @default.
• W3149192734 cites W3034431451 @default.
• W3149192734 cites W3034566390 @default.
• W3149192734 cites W3034600949 @default.
• W3149192734 cites W3034968345 @default.
• W3149192734 cites W3035148830 @default.
• W3149192734 cites W3035574324 @default.
• W3149192734 cites W3035653890 @default.
• W3149192734 cites W3036499167 @default.
• W3149192734 cites W3037211062 @default.
• W3149192734 cites W3042843949 @default.
• W3149192734 cites W3047275688 @default.
• W3149192734 cites W3092948912 @default.
• W3149192734 cites W3099018226 @default.
• W3149192734 cites W3101267796 @default.
• W3149192734 cites W3103242287 @default.
• W3149192734 cites W3105675572 @default.
• W3149192734 cites W3106721533 @default.
• W3149192734 cites W3107517429 @default.
• W3149192734 cites W3109547540 @default.
• W3149192734 cites W3109585842 @default.
• W3149192734 cites W3112108866 @default.
• W3149192734 cites W3121147178 @default.
• W3149192734 cites W3127762346 @default.
• W3149192734 cites W3130983693 @default.
• W3149192734 cites W3176179930 @default.
• W3149192734 hasPublicationYear "2021" @default.
• W3149192734 type Work @default.
• W3149192734 sameAs 3149192734 @default.
• W3149192734 citedByCount "4" @default.
• W3149192734 countsByYear W31491927342021 @default.
• W3149192734 crossrefType "posted-content" @default.
• W3149192734 hasAuthorship W3149192734A5016606943 @default.
• W3149192734 hasAuthorship W3149192734A5088795883 @default.
• W3149192734 hasConcept C110898773 @default.
• W3149192734 hasConcept C115961682 @default.
• W3149192734 hasConcept C120515352 @default.
• W3149192734 hasConcept C121332964 @default.
• W3149192734 hasConcept C154945302 @default.
• W3149192734 hasConcept C163258240 @default.
• W3149192734 hasConcept C167966045 @default.
• W3149192734 hasConcept C2776436953 @default.
• W3149192734 hasConcept C2780992000 @default.
• W3149192734 hasConcept C2908650547 @default.
• W3149192734 hasConcept C31972630 @default.
• W3149192734 hasConcept C39890363 @default.
• W3149192734 hasConcept C41008148 @default.
• W3149192734 hasConcept C62520636 @default.
• W3149192734 hasConcept C94816000 @default.

• next