Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384080216> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4384080216 endingPage "13" @default.
- W4384080216 startingPage "1" @default.
- W4384080216 abstract "In this study, we address the challenge of estimating 3D body pose, shape, and depth relationships from single RGB images in crowded scenes. The difficulty lies in the limited availability of in-the-wild training samples, which feature densely populated scenes. To mitigate this issue, we introduce a synthesis-based approach that fuses multiple human samples into a single composite scene. Our innovative scene-aware blending technique maintains human-scene consistency by positioning individuals within plausible locations and adjusting their scales to conform to 3D settings. Furthermore, our method enables flexible per-subject occlusion management during the blending process, bolstering the robustness of 3D human body representations through a novel de-occlusion training scheme. We present a one-stage model, CBD, designed to learn monocular regression of 3D people in crowds by leveraging blending and de-occlusion techniques. Our quantitative and qualitative evaluations on four benchmark datasets reveal that CBD surpasses existing state-of-the-art approaches in terms of 3D human pose and mesh regression accuracy, thereby establishing it as a promising solution for monocular 3D human mesh recovery in densely populated scenes." @default.
- W4384080216 created "2023-07-13" @default.
- W4384080216 creator A5008597054 @default.
- W4384080216 creator A5013246830 @default.
- W4384080216 creator A5018566863 @default.
- W4384080216 creator A5036020028 @default.
- W4384080216 creator A5070508316 @default.
- W4384080216 creator A5083680911 @default.
- W4384080216 date "2023-01-01" @default.
- W4384080216 modified "2023-09-28" @default.
- W4384080216 title "Learning Monocular Regression of 3D People in Crowds via Scene-aware Blending and De-occlusion" @default.
- W4384080216 doi "https://doi.org/10.1109/tmm.2023.3294820" @default.
- W4384080216 hasPublicationYear "2023" @default.
- W4384080216 type Work @default.
- W4384080216 citedByCount "0" @default.
- W4384080216 crossrefType "journal-article" @default.
- W4384080216 hasAuthorship W4384080216A5008597054 @default.
- W4384080216 hasAuthorship W4384080216A5013246830 @default.
- W4384080216 hasAuthorship W4384080216A5018566863 @default.
- W4384080216 hasAuthorship W4384080216A5036020028 @default.
- W4384080216 hasAuthorship W4384080216A5070508316 @default.
- W4384080216 hasAuthorship W4384080216A5083680911 @default.
- W4384080216 hasConcept C104317684 @default.
- W4384080216 hasConcept C105795698 @default.
- W4384080216 hasConcept C13280743 @default.
- W4384080216 hasConcept C153180895 @default.
- W4384080216 hasConcept C154945302 @default.
- W4384080216 hasConcept C164705383 @default.
- W4384080216 hasConcept C185592680 @default.
- W4384080216 hasConcept C185798385 @default.
- W4384080216 hasConcept C205649164 @default.
- W4384080216 hasConcept C2776268601 @default.
- W4384080216 hasConcept C2777852691 @default.
- W4384080216 hasConcept C31972630 @default.
- W4384080216 hasConcept C33923547 @default.
- W4384080216 hasConcept C38652104 @default.
- W4384080216 hasConcept C41008148 @default.
- W4384080216 hasConcept C52622490 @default.
- W4384080216 hasConcept C55493867 @default.
- W4384080216 hasConcept C63479239 @default.
- W4384080216 hasConcept C65909025 @default.
- W4384080216 hasConcept C71924100 @default.
- W4384080216 hasConcept C82990744 @default.
- W4384080216 hasConcept C83546350 @default.
- W4384080216 hasConceptScore W4384080216C104317684 @default.
- W4384080216 hasConceptScore W4384080216C105795698 @default.
- W4384080216 hasConceptScore W4384080216C13280743 @default.
- W4384080216 hasConceptScore W4384080216C153180895 @default.
- W4384080216 hasConceptScore W4384080216C154945302 @default.
- W4384080216 hasConceptScore W4384080216C164705383 @default.
- W4384080216 hasConceptScore W4384080216C185592680 @default.
- W4384080216 hasConceptScore W4384080216C185798385 @default.
- W4384080216 hasConceptScore W4384080216C205649164 @default.
- W4384080216 hasConceptScore W4384080216C2776268601 @default.
- W4384080216 hasConceptScore W4384080216C2777852691 @default.
- W4384080216 hasConceptScore W4384080216C31972630 @default.
- W4384080216 hasConceptScore W4384080216C33923547 @default.
- W4384080216 hasConceptScore W4384080216C38652104 @default.
- W4384080216 hasConceptScore W4384080216C41008148 @default.
- W4384080216 hasConceptScore W4384080216C52622490 @default.
- W4384080216 hasConceptScore W4384080216C55493867 @default.
- W4384080216 hasConceptScore W4384080216C63479239 @default.
- W4384080216 hasConceptScore W4384080216C65909025 @default.
- W4384080216 hasConceptScore W4384080216C71924100 @default.
- W4384080216 hasConceptScore W4384080216C82990744 @default.
- W4384080216 hasConceptScore W4384080216C83546350 @default.
- W4384080216 hasLocation W43840802161 @default.
- W4384080216 hasOpenAccess W4384080216 @default.
- W4384080216 hasPrimaryLocation W43840802161 @default.
- W4384080216 hasRelatedWork W1602592726 @default.
- W4384080216 hasRelatedWork W1999222583 @default.
- W4384080216 hasRelatedWork W2241457321 @default.
- W4384080216 hasRelatedWork W2794771666 @default.
- W4384080216 hasRelatedWork W2921707373 @default.
- W4384080216 hasRelatedWork W2980357211 @default.
- W4384080216 hasRelatedWork W2980953096 @default.
- W4384080216 hasRelatedWork W3102636071 @default.
- W4384080216 hasRelatedWork W4298315644 @default.
- W4384080216 hasRelatedWork W4321512589 @default.
- W4384080216 isParatext "false" @default.
- W4384080216 isRetracted "false" @default.
- W4384080216 workType "article" @default.