Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386071572> ?p ?o ?g. }
- W4386071572 abstract "This paper presents a method to reconstruct a complete human geometry and texture from an image of a person with only partial body observed, e.g., a torso. The core challenge arises from the occlusion: there exists no pixel to reconstruct where many existing single-view human reconstruction methods are not designed to handle such invisible parts, leading to missing data in 3D. To address this challenge, we introduce a novel coarse-to-fine human reconstruction framework. For coarse reconstruction, explicit volumetric features are learned to generate a complete human geometry with 3D convolutional neural networks conditioned by a 3D body model and the style features from visible parts. An implicit network combines the learned 3D features with the high-quality surface normals enhanced from multiviews to produce fine local details, e.g., high-frequency wrinkles. Finally, we perform progressive texture inpainting to reconstruct a complete appearance of the person in a view-consistent way, which is not possible without the reconstruction of a complete geometry. In experiments, we demonstrate that our method can reconstruct high-quality 3D humans, which is robust to occlusion." @default.
- W4386071572 created "2023-08-23" @default.
- W4386071572 creator A5029316647 @default.
- W4386071572 creator A5036138328 @default.
- W4386071572 creator A5082091356 @default.
- W4386071572 creator A5082235583 @default.
- W4386071572 creator A5089480358 @default.
- W4386071572 date "2023-06-01" @default.
- W4386071572 modified "2023-10-16" @default.
- W4386071572 title "Complete 3D Human Reconstruction from a Single Incomplete Image" @default.
- W4386071572 cites W1967554269 @default.
- W4386071572 cites W2471768434 @default.
- W4386071572 cites W2559085405 @default.
- W4386071572 cites W2560722161 @default.
- W4386071572 cites W2698857938 @default.
- W4386071572 cites W2798637590 @default.
- W4386071572 cites W2896145365 @default.
- W4386071572 cites W2962849139 @default.
- W4386071572 cites W2963630103 @default.
- W4386071572 cites W2963876278 @default.
- W4386071572 cites W2963907666 @default.
- W4386071572 cites W2963926543 @default.
- W4386071572 cites W2963995996 @default.
- W4386071572 cites W2971467054 @default.
- W4386071572 cites W2978956737 @default.
- W4386071572 cites W2981514602 @default.
- W4386071572 cites W2981637078 @default.
- W4386071572 cites W2981978060 @default.
- W4386071572 cites W2986615800 @default.
- W4386071572 cites W2991621301 @default.
- W4386071572 cites W3034259269 @default.
- W4386071572 cites W3035291735 @default.
- W4386071572 cites W3035492592 @default.
- W4386071572 cites W3041416670 @default.
- W4386071572 cites W3096831136 @default.
- W4386071572 cites W3174025609 @default.
- W4386071572 cites W3174541392 @default.
- W4386071572 cites W3175408382 @default.
- W4386071572 cites W3176568184 @default.
- W4386071572 cites W3202432020 @default.
- W4386071572 cites W3204956438 @default.
- W4386071572 cites W3209771269 @default.
- W4386071572 cites W4200095354 @default.
- W4386071572 cites W4205355655 @default.
- W4386071572 cites W4226160668 @default.
- W4386071572 cites W4233857083 @default.
- W4386071572 cites W4312728108 @default.
- W4386071572 cites W4312874524 @default.
- W4386071572 cites W4312933868 @default.
- W4386071572 cites W4313175219 @default.
- W4386071572 doi "https://doi.org/10.1109/cvpr52729.2023.00845" @default.
- W4386071572 hasPublicationYear "2023" @default.
- W4386071572 type Work @default.
- W4386071572 citedByCount "0" @default.
- W4386071572 crossrefType "proceedings-article" @default.
- W4386071572 hasAuthorship W4386071572A5029316647 @default.
- W4386071572 hasAuthorship W4386071572A5036138328 @default.
- W4386071572 hasAuthorship W4386071572A5082091356 @default.
- W4386071572 hasAuthorship W4386071572A5082235583 @default.
- W4386071572 hasAuthorship W4386071572A5089480358 @default.
- W4386071572 hasConcept C105702510 @default.
- W4386071572 hasConcept C109950114 @default.
- W4386071572 hasConcept C115961682 @default.
- W4386071572 hasConcept C11727466 @default.
- W4386071572 hasConcept C141379421 @default.
- W4386071572 hasConcept C154945302 @default.
- W4386071572 hasConcept C20885615 @default.
- W4386071572 hasConcept C2524010 @default.
- W4386071572 hasConcept C2776799497 @default.
- W4386071572 hasConcept C2781195486 @default.
- W4386071572 hasConcept C31972630 @default.
- W4386071572 hasConcept C33923547 @default.
- W4386071572 hasConcept C41008148 @default.
- W4386071572 hasConcept C523889960 @default.
- W4386071572 hasConcept C71924100 @default.
- W4386071572 hasConcept C81363708 @default.
- W4386071572 hasConceptScore W4386071572C105702510 @default.
- W4386071572 hasConceptScore W4386071572C109950114 @default.
- W4386071572 hasConceptScore W4386071572C115961682 @default.
- W4386071572 hasConceptScore W4386071572C11727466 @default.
- W4386071572 hasConceptScore W4386071572C141379421 @default.
- W4386071572 hasConceptScore W4386071572C154945302 @default.
- W4386071572 hasConceptScore W4386071572C20885615 @default.
- W4386071572 hasConceptScore W4386071572C2524010 @default.
- W4386071572 hasConceptScore W4386071572C2776799497 @default.
- W4386071572 hasConceptScore W4386071572C2781195486 @default.
- W4386071572 hasConceptScore W4386071572C31972630 @default.
- W4386071572 hasConceptScore W4386071572C33923547 @default.
- W4386071572 hasConceptScore W4386071572C41008148 @default.
- W4386071572 hasConceptScore W4386071572C523889960 @default.
- W4386071572 hasConceptScore W4386071572C71924100 @default.
- W4386071572 hasConceptScore W4386071572C81363708 @default.
- W4386071572 hasLocation W43860715721 @default.
- W4386071572 hasOpenAccess W4386071572 @default.
- W4386071572 hasPrimaryLocation W43860715721 @default.
- W4386071572 hasRelatedWork W2094002035 @default.
- W4386071572 hasRelatedWork W2382799321 @default.
- W4386071572 hasRelatedWork W2517246325 @default.
- W4386071572 hasRelatedWork W2534204995 @default.
- W4386071572 hasRelatedWork W2542462829 @default.