Matches in SemOpenAlex for { <https://semopenalex.org/work/W4353073792> ?p ?o ?g. }
- W4353073792 abstract "Abstract Learning-based approaches have made substantial progress in capturing spatially-varying bidirectional reflectance distribution functions (SVBRDFs) from a single image with unknown lighting and geometry. However, most existing networks only consider per-pixel losses which limit their capability to recover local features such as smooth glossy regions. A few generative adversarial networks use multiple discriminators for different parameter maps, increasing network complexity. We present a novel end-to-end generative adversarial network (GAN) to recover appearance from a single picture of a nearly-flat surface lit by flash. We use a single unified adversarial framework for each parameter map. An attention module guides the network to focus on details of the maps. Furthermore, the SVBRDF map loss is combined to prevent paying excess attention to specular highlights. We demonstrate and evaluate our method on both public datasets and real data. Quantitative analysis and visual comparisons indicate that our method achieves better results than the state-of-the-art in most cases." @default.
- W4353073792 created "2023-03-23" @default.
- W4353073792 creator A5016012780 @default.
- W4353073792 creator A5023819131 @default.
- W4353073792 creator A5046773256 @default.
- W4353073792 date "2023-03-22" @default.
- W4353073792 modified "2023-10-18" @default.
- W4353073792 title "An attention-embedded GAN for SVBRDF recovery from a single image" @default.
- W4353073792 cites W1600855323 @default.
- W4353073792 cites W1901129140 @default.
- W4353073792 cites W1994352258 @default.
- W4353073792 cites W2104587129 @default.
- W4353073792 cites W2106313016 @default.
- W4353073792 cites W2106726792 @default.
- W4353073792 cites W2197110667 @default.
- W4353073792 cites W2242654827 @default.
- W4353073792 cites W2402026173 @default.
- W4353073792 cites W2475362300 @default.
- W4353073792 cites W2554498528 @default.
- W4353073792 cites W2554929906 @default.
- W4353073792 cites W2736596523 @default.
- W4353073792 cites W2756464018 @default.
- W4353073792 cites W2811490555 @default.
- W4353073792 cites W2898348749 @default.
- W4353073792 cites W2903365351 @default.
- W4353073792 cites W2958302123 @default.
- W4353073792 cites W2963073614 @default.
- W4353073792 cites W2963650738 @default.
- W4353073792 cites W2964228590 @default.
- W4353073792 cites W2965557046 @default.
- W4353073792 cites W3035574324 @default.
- W4353073792 cites W3039219616 @default.
- W4353073792 cites W3090135481 @default.
- W4353073792 cites W3110182603 @default.
- W4353073792 cites W3128051178 @default.
- W4353073792 cites W3166355208 @default.
- W4353073792 cites W3185905868 @default.
- W4353073792 cites W3208624098 @default.
- W4353073792 cites W4251547822 @default.
- W4353073792 doi "https://doi.org/10.1007/s41095-022-0289-1" @default.
- W4353073792 hasPublicationYear "2023" @default.
- W4353073792 type Work @default.
- W4353073792 citedByCount "0" @default.
- W4353073792 crossrefType "journal-article" @default.
- W4353073792 hasAuthorship W4353073792A5016012780 @default.
- W4353073792 hasAuthorship W4353073792A5023819131 @default.
- W4353073792 hasAuthorship W4353073792A5046773256 @default.
- W4353073792 hasBestOaLocation W43530737921 @default.
- W4353073792 hasConcept C108583219 @default.
- W4353073792 hasConcept C115961682 @default.
- W4353073792 hasConcept C118381688 @default.
- W4353073792 hasConcept C120665830 @default.
- W4353073792 hasConcept C121332964 @default.
- W4353073792 hasConcept C121684516 @default.
- W4353073792 hasConcept C134306372 @default.
- W4353073792 hasConcept C151201525 @default.
- W4353073792 hasConcept C154945302 @default.
- W4353073792 hasConcept C160633673 @default.
- W4353073792 hasConcept C192209626 @default.
- W4353073792 hasConcept C21442007 @default.
- W4353073792 hasConcept C2988773926 @default.
- W4353073792 hasConcept C31972630 @default.
- W4353073792 hasConcept C33923547 @default.
- W4353073792 hasConcept C37736160 @default.
- W4353073792 hasConcept C39890363 @default.
- W4353073792 hasConcept C41008148 @default.
- W4353073792 hasConcept C77660652 @default.
- W4353073792 hasConceptScore W4353073792C108583219 @default.
- W4353073792 hasConceptScore W4353073792C115961682 @default.
- W4353073792 hasConceptScore W4353073792C118381688 @default.
- W4353073792 hasConceptScore W4353073792C120665830 @default.
- W4353073792 hasConceptScore W4353073792C121332964 @default.
- W4353073792 hasConceptScore W4353073792C121684516 @default.
- W4353073792 hasConceptScore W4353073792C134306372 @default.
- W4353073792 hasConceptScore W4353073792C151201525 @default.
- W4353073792 hasConceptScore W4353073792C154945302 @default.
- W4353073792 hasConceptScore W4353073792C160633673 @default.
- W4353073792 hasConceptScore W4353073792C192209626 @default.
- W4353073792 hasConceptScore W4353073792C21442007 @default.
- W4353073792 hasConceptScore W4353073792C2988773926 @default.
- W4353073792 hasConceptScore W4353073792C31972630 @default.
- W4353073792 hasConceptScore W4353073792C33923547 @default.
- W4353073792 hasConceptScore W4353073792C37736160 @default.
- W4353073792 hasConceptScore W4353073792C39890363 @default.
- W4353073792 hasConceptScore W4353073792C41008148 @default.
- W4353073792 hasConceptScore W4353073792C77660652 @default.
- W4353073792 hasLocation W43530737921 @default.
- W4353073792 hasOpenAccess W4353073792 @default.
- W4353073792 hasPrimaryLocation W43530737921 @default.
- W4353073792 hasRelatedWork W2756954956 @default.
- W4353073792 hasRelatedWork W2982455199 @default.
- W4353073792 hasRelatedWork W3014413679 @default.
- W4353073792 hasRelatedWork W3024390022 @default.
- W4353073792 hasRelatedWork W3156291593 @default.
- W4353073792 hasRelatedWork W3178813832 @default.
- W4353073792 hasRelatedWork W4309087524 @default.
- W4353073792 hasRelatedWork W4312835269 @default.
- W4353073792 hasRelatedWork W4313479464 @default.
- W4353073792 hasRelatedWork W4353073792 @default.
- W4353073792 isParatext "false" @default.