Matches in SemOpenAlex for { <https://semopenalex.org/work/W4284663764> ?p ?o ?g. }
- W4284663764 endingPage "4692" @default.
- W4284663764 startingPage "4679" @default.
- W4284663764 abstract "In this work, we focus on the task of multi-person mesh recovery from a single color image, where the key issue is to tackle the pixel-level ambiguities caused by inter-person occlusions. Overall, there are two main technical challenges when addressing the ambiguities: how to extract valid target features under occlusions and how to reconstruct reasonable human meshes with only a handful of body cues? To deal with these problems, our key idea is to utilize the predicted 2D poses to locate and separate the target person, and reconstruct them with a novel learning-based UV prior. Specifically, we propose a visible pose-mask module to help extract valid target features, then train a dense body mesh prior to promote reconstructing natural mesh represented by the UV position map. To evaluate the performance of our proposed method under occlusions, we further build an in-the-wild 3D multi-person benchmark named as 3DMPB. Experimental results demonstrate that our method achieves state-of-the-art compared with previous methods. The dataset, codes are publicly available on our website." @default.
- W4284663764 created "2022-07-08" @default.
- W4284663764 creator A5014074712 @default.
- W4284663764 creator A5067908031 @default.
- W4284663764 creator A5078053611 @default.
- W4284663764 date "2022-01-01" @default.
- W4284663764 modified "2023-09-26" @default.
- W4284663764 title "Pose2UV: Single-Shot Multiperson Mesh Recovery With Deep UV Prior" @default.
- W4284663764 cites W1967554269 @default.
- W4284663764 cites W2005984284 @default.
- W4284663764 cites W2080873731 @default.
- W4284663764 cites W2101032778 @default.
- W4284663764 cites W2103015390 @default.
- W4284663764 cites W2122633688 @default.
- W4284663764 cites W2135533529 @default.
- W4284663764 cites W2135826343 @default.
- W4284663764 cites W2194775991 @default.
- W4284663764 cites W2573098616 @default.
- W4284663764 cites W2771965516 @default.
- W4284663764 cites W2798411580 @default.
- W4284663764 cites W2798637590 @default.
- W4284663764 cites W2888934629 @default.
- W4284663764 cites W2894878561 @default.
- W4284663764 cites W2898498111 @default.
- W4284663764 cites W2900273708 @default.
- W4284663764 cites W2916798096 @default.
- W4284663764 cites W2958537753 @default.
- W4284663764 cites W2962730651 @default.
- W4284663764 cites W2962793481 @default.
- W4284663764 cites W2962954622 @default.
- W4284663764 cites W2963150697 @default.
- W4284663764 cites W2963515833 @default.
- W4284663764 cites W2963781481 @default.
- W4284663764 cites W2963907666 @default.
- W4284663764 cites W2963995996 @default.
- W4284663764 cites W2971467054 @default.
- W4284663764 cites W2971856312 @default.
- W4284663764 cites W2978956737 @default.
- W4284663764 cites W2981637078 @default.
- W4284663764 cites W2982480216 @default.
- W4284663764 cites W2990270790 @default.
- W4284663764 cites W2998273692 @default.
- W4284663764 cites W3012111401 @default.
- W4284663764 cites W3035186639 @default.
- W4284663764 cites W3035191304 @default.
- W4284663764 cites W3035501466 @default.
- W4284663764 cites W3035551320 @default.
- W4284663764 cites W3097539092 @default.
- W4284663764 cites W3101560663 @default.
- W4284663764 cites W3107167007 @default.
- W4284663764 cites W3107346586 @default.
- W4284663764 cites W3107944344 @default.
- W4284663764 cites W3108664802 @default.
- W4284663764 cites W3195962267 @default.
- W4284663764 cites W4225998098 @default.
- W4284663764 doi "https://doi.org/10.1109/tip.2022.3187294" @default.
- W4284663764 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35793292" @default.
- W4284663764 hasPublicationYear "2022" @default.
- W4284663764 type Work @default.
- W4284663764 citedByCount "0" @default.
- W4284663764 crossrefType "journal-article" @default.
- W4284663764 hasAuthorship W4284663764A5014074712 @default.
- W4284663764 hasAuthorship W4284663764A5067908031 @default.
- W4284663764 hasAuthorship W4284663764A5078053611 @default.
- W4284663764 hasConcept C10138342 @default.
- W4284663764 hasConcept C108583219 @default.
- W4284663764 hasConcept C120665830 @default.
- W4284663764 hasConcept C121332964 @default.
- W4284663764 hasConcept C121684516 @default.
- W4284663764 hasConcept C13280743 @default.
- W4284663764 hasConcept C153180895 @default.
- W4284663764 hasConcept C154945302 @default.
- W4284663764 hasConcept C160633673 @default.
- W4284663764 hasConcept C162324750 @default.
- W4284663764 hasConcept C185798385 @default.
- W4284663764 hasConcept C192209626 @default.
- W4284663764 hasConcept C198082294 @default.
- W4284663764 hasConcept C205649164 @default.
- W4284663764 hasConcept C26517878 @default.
- W4284663764 hasConcept C31487907 @default.
- W4284663764 hasConcept C31972630 @default.
- W4284663764 hasConcept C38652104 @default.
- W4284663764 hasConcept C41008148 @default.
- W4284663764 hasConceptScore W4284663764C10138342 @default.
- W4284663764 hasConceptScore W4284663764C108583219 @default.
- W4284663764 hasConceptScore W4284663764C120665830 @default.
- W4284663764 hasConceptScore W4284663764C121332964 @default.
- W4284663764 hasConceptScore W4284663764C121684516 @default.
- W4284663764 hasConceptScore W4284663764C13280743 @default.
- W4284663764 hasConceptScore W4284663764C153180895 @default.
- W4284663764 hasConceptScore W4284663764C154945302 @default.
- W4284663764 hasConceptScore W4284663764C160633673 @default.
- W4284663764 hasConceptScore W4284663764C162324750 @default.
- W4284663764 hasConceptScore W4284663764C185798385 @default.
- W4284663764 hasConceptScore W4284663764C192209626 @default.
- W4284663764 hasConceptScore W4284663764C198082294 @default.
- W4284663764 hasConceptScore W4284663764C205649164 @default.
- W4284663764 hasConceptScore W4284663764C26517878 @default.