Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386076125> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4386076125 abstract "We propose VDN-NeRF, a method to train neural radiance fields (NeRFs) for better geometry under non-Lambertian surface and dynamic lighting conditions that cause significant variation in the radiance of a point when viewed from different angles. Instead of explicitly modeling the underlying factors that result in the view-dependent phenomenon, which could be complex yet not inclusive, we develop a simple and effective technique that normalizes the view-dependence by distilling invariant information already encoded in the learned NeRFs. We then jointly train NeRFs for view synthesis with view-dependence normalization to attain quality geometry. Our experiments show that even though shape-radiance ambiguity is inevitable, the proposed normalization can minimize its effect on geometry, which essentially aligns the optimal capacity needed for explaining view-dependent variations. Our method applies to various baselines and significantly improves geometry without changing the volume rendering pipeline, even if the data is captured under a moving light source. Code is available at: https://github.com/BoifZ/VDN-NeRF." @default.
- W4386076125 created "2023-08-23" @default.
- W4386076125 creator A5008066397 @default.
- W4386076125 creator A5008766810 @default.
- W4386076125 creator A5065368881 @default.
- W4386076125 creator A5078012796 @default.
- W4386076125 creator A5083012411 @default.
- W4386076125 date "2023-06-01" @default.
- W4386076125 modified "2023-10-01" @default.
- W4386076125 title "VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization" @default.
- W4386076125 cites W2554929906 @default.
- W4386076125 cites W2903365351 @default.
- W4386076125 cites W2963446712 @default.
- W4386076125 cites W2963876827 @default.
- W4386076125 cites W3034304664 @default.
- W4386076125 cites W3034964128 @default.
- W4386076125 cites W3035257660 @default.
- W4386076125 cites W3100009925 @default.
- W4386076125 cites W3134621679 @default.
- W4386076125 cites W3147924083 @default.
- W4386076125 cites W3154129649 @default.
- W4386076125 cites W3174581459 @default.
- W4386076125 cites W3175488633 @default.
- W4386076125 cites W3176368002 @default.
- W4386076125 cites W3182714435 @default.
- W4386076125 cites W3184952021 @default.
- W4386076125 cites W3202037070 @default.
- W4386076125 cites W3202995573 @default.
- W4386076125 cites W3203257492 @default.
- W4386076125 cites W3203570626 @default.
- W4386076125 cites W3204455502 @default.
- W4386076125 cites W4200313684 @default.
- W4386076125 cites W4214564845 @default.
- W4386076125 cites W4214579621 @default.
- W4386076125 cites W4214748949 @default.
- W4386076125 cites W4233857083 @default.
- W4386076125 cites W4286611058 @default.
- W4386076125 cites W4311801991 @default.
- W4386076125 cites W4312325284 @default.
- W4386076125 cites W4312679369 @default.
- W4386076125 cites W4312969460 @default.
- W4386076125 cites W4312980099 @default.
- W4386076125 cites W4313165271 @default.
- W4386076125 doi "https://doi.org/10.1109/cvpr52729.2023.00012" @default.
- W4386076125 hasPublicationYear "2023" @default.
- W4386076125 type Work @default.
- W4386076125 citedByCount "1" @default.
- W4386076125 countsByYear W43860761252023 @default.
- W4386076125 crossrefType "proceedings-article" @default.
- W4386076125 hasAuthorship W4386076125A5008066397 @default.
- W4386076125 hasAuthorship W4386076125A5008766810 @default.
- W4386076125 hasAuthorship W4386076125A5065368881 @default.
- W4386076125 hasAuthorship W4386076125A5078012796 @default.
- W4386076125 hasAuthorship W4386076125A5083012411 @default.
- W4386076125 hasConcept C120665830 @default.
- W4386076125 hasConcept C121332964 @default.
- W4386076125 hasConcept C136886441 @default.
- W4386076125 hasConcept C144024400 @default.
- W4386076125 hasConcept C154945302 @default.
- W4386076125 hasConcept C19165224 @default.
- W4386076125 hasConcept C199360897 @default.
- W4386076125 hasConcept C23690007 @default.
- W4386076125 hasConcept C2524010 @default.
- W4386076125 hasConcept C2780522230 @default.
- W4386076125 hasConcept C31972630 @default.
- W4386076125 hasConcept C33923547 @default.
- W4386076125 hasConcept C41008148 @default.
- W4386076125 hasConceptScore W4386076125C120665830 @default.
- W4386076125 hasConceptScore W4386076125C121332964 @default.
- W4386076125 hasConceptScore W4386076125C136886441 @default.
- W4386076125 hasConceptScore W4386076125C144024400 @default.
- W4386076125 hasConceptScore W4386076125C154945302 @default.
- W4386076125 hasConceptScore W4386076125C19165224 @default.
- W4386076125 hasConceptScore W4386076125C199360897 @default.
- W4386076125 hasConceptScore W4386076125C23690007 @default.
- W4386076125 hasConceptScore W4386076125C2524010 @default.
- W4386076125 hasConceptScore W4386076125C2780522230 @default.
- W4386076125 hasConceptScore W4386076125C31972630 @default.
- W4386076125 hasConceptScore W4386076125C33923547 @default.
- W4386076125 hasConceptScore W4386076125C41008148 @default.
- W4386076125 hasLocation W43860761251 @default.
- W4386076125 hasOpenAccess W4386076125 @default.
- W4386076125 hasPrimaryLocation W43860761251 @default.
- W4386076125 hasRelatedWork W1540444031 @default.
- W4386076125 hasRelatedWork W1602413925 @default.
- W4386076125 hasRelatedWork W1891287906 @default.
- W4386076125 hasRelatedWork W1969923398 @default.
- W4386076125 hasRelatedWork W2004978530 @default.
- W4386076125 hasRelatedWork W2036807459 @default.
- W4386076125 hasRelatedWork W2533072256 @default.
- W4386076125 hasRelatedWork W2772917594 @default.
- W4386076125 hasRelatedWork W2775347418 @default.
- W4386076125 hasRelatedWork W4220912900 @default.
- W4386076125 isParatext "false" @default.
- W4386076125 isRetracted "false" @default.
- W4386076125 workType "article" @default.