Matches in SemOpenAlex for { <https://semopenalex.org/work/W3192966712> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W3192966712 abstract "Recent neural rendering approaches for human activities achieve remarkable view synthesis results, but still rely on dense input views or dense training with all the capture frames, leading to deployment difficulty and inefficient training overload. However, existing advances will be ill-posed if the input is both spatially and temporally sparse. To fill this gap, in this paper we propose a few-shot neural human rendering approach (FNHR) from only sparse RGBD inputs, which exploits the temporal and spatial redundancy to generate photo-realistic free-view output of human activities. Our FNHR is trained only on the key-frames which expand the motion manifold in the input sequences. We introduce a two-branch neural blending to combine the neural point render and classical graphics texturing pipeline, which integrates reliable observations over sparse key-frames. Furthermore, we adopt a patch-based adversarial training process to make use of the local redundancy and avoids over-fitting to the key-frames, which generates fine-detailed rendering results. Extensive experiments demonstrate the effectiveness of our approach to generate high-quality free view-point results for challenging human performances under the sparse setting." @default.
- W3192966712 created "2021-08-16" @default.
- W3192966712 creator A5015086148 @default.
- W3192966712 creator A5028462736 @default.
- W3192966712 creator A5045684529 @default.
- W3192966712 creator A5054640343 @default.
- W3192966712 creator A5074244240 @default.
- W3192966712 creator A5085836060 @default.
- W3192966712 date "2021-08-01" @default.
- W3192966712 modified "2023-09-27" @default.
- W3192966712 title "Few-shot Neural Human Performance Rendering from Sparse RGBD Videos" @default.
- W3192966712 cites W1901129140 @default.
- W3192966712 cites W2520806793 @default.
- W3192966712 cites W2559085405 @default.
- W3192966712 cites W2768345177 @default.
- W3192966712 cites W2901584762 @default.
- W3192966712 cites W2942074357 @default.
- W3192966712 cites W2944041518 @default.
- W3192966712 cites W2946584893 @default.
- W3192966712 cites W2963515833 @default.
- W3192966712 cites W2963627347 @default.
- W3192966712 cites W2963873475 @default.
- W3192966712 cites W3011537551 @default.
- W3192966712 cites W3032437359 @default.
- W3192966712 cites W3034671389 @default.
- W3192966712 cites W3035678981 @default.
- W3192966712 cites W3096718826 @default.
- W3192966712 cites W3100398946 @default.
- W3192966712 cites W3107486934 @default.
- W3192966712 cites W3108311884 @default.
- W3192966712 cites W3114462840 @default.
- W3192966712 cites W3179249536 @default.
- W3192966712 cites W3189670121 @default.
- W3192966712 doi "https://doi.org/10.24963/ijcai.2021/130" @default.
- W3192966712 hasPublicationYear "2021" @default.
- W3192966712 type Work @default.
- W3192966712 sameAs 3192966712 @default.
- W3192966712 citedByCount "5" @default.
- W3192966712 countsByYear W31929667122021 @default.
- W3192966712 countsByYear W31929667122022 @default.
- W3192966712 crossrefType "proceedings-article" @default.
- W3192966712 hasAuthorship W3192966712A5015086148 @default.
- W3192966712 hasAuthorship W3192966712A5028462736 @default.
- W3192966712 hasAuthorship W3192966712A5045684529 @default.
- W3192966712 hasAuthorship W3192966712A5054640343 @default.
- W3192966712 hasAuthorship W3192966712A5074244240 @default.
- W3192966712 hasAuthorship W3192966712A5085836060 @default.
- W3192966712 hasBestOaLocation W31929667121 @default.
- W3192966712 hasConcept C111919701 @default.
- W3192966712 hasConcept C152124472 @default.
- W3192966712 hasConcept C154945302 @default.
- W3192966712 hasConcept C165696696 @default.
- W3192966712 hasConcept C173552908 @default.
- W3192966712 hasConcept C205711294 @default.
- W3192966712 hasConcept C31972630 @default.
- W3192966712 hasConcept C38652104 @default.
- W3192966712 hasConcept C41008148 @default.
- W3192966712 hasConcept C50644808 @default.
- W3192966712 hasConcept C66629338 @default.
- W3192966712 hasConcept C77660652 @default.
- W3192966712 hasConceptScore W3192966712C111919701 @default.
- W3192966712 hasConceptScore W3192966712C152124472 @default.
- W3192966712 hasConceptScore W3192966712C154945302 @default.
- W3192966712 hasConceptScore W3192966712C165696696 @default.
- W3192966712 hasConceptScore W3192966712C173552908 @default.
- W3192966712 hasConceptScore W3192966712C205711294 @default.
- W3192966712 hasConceptScore W3192966712C31972630 @default.
- W3192966712 hasConceptScore W3192966712C38652104 @default.
- W3192966712 hasConceptScore W3192966712C41008148 @default.
- W3192966712 hasConceptScore W3192966712C50644808 @default.
- W3192966712 hasConceptScore W3192966712C66629338 @default.
- W3192966712 hasConceptScore W3192966712C77660652 @default.
- W3192966712 hasLocation W31929667121 @default.
- W3192966712 hasLocation W31929667122 @default.
- W3192966712 hasLocation W31929667123 @default.
- W3192966712 hasOpenAccess W3192966712 @default.
- W3192966712 hasPrimaryLocation W31929667121 @default.
- W3192966712 hasRelatedWork W1503414886 @default.
- W3192966712 hasRelatedWork W1863533157 @default.
- W3192966712 hasRelatedWork W2048402902 @default.
- W3192966712 hasRelatedWork W2095660797 @default.
- W3192966712 hasRelatedWork W2112614329 @default.
- W3192966712 hasRelatedWork W2740010476 @default.
- W3192966712 hasRelatedWork W2797881514 @default.
- W3192966712 hasRelatedWork W3187331046 @default.
- W3192966712 hasRelatedWork W60029494 @default.
- W3192966712 hasRelatedWork W3182299699 @default.
- W3192966712 isParatext "false" @default.
- W3192966712 isRetracted "false" @default.
- W3192966712 magId "3192966712" @default.
- W3192966712 workType "article" @default.