Matches in SemOpenAlex for { <https://semopenalex.org/work/W3206989860> ?p ?o ?g. }
Showing items 1 to 99 of
99
with 100 items per page.
- W3206989860 abstract "The ability to estimate the 3D human shape and pose from images can be useful in many contexts. Recent approaches have explored using graph convolutional networks and achieved promising results. The fact that the 3D shape is represented by a mesh, an undirected graph, makes graph convolutional networks a natural fit for this problem. However, graph convolutional networks have limited representation power. Information from nodes in the graph is passed to connected neighbors, and propagation of information requires successive graph convolutions. To overcome this limitation, we propose a dual-scale graph approach. We use a coarse graph, derived from a dense graph, to estimate the human's 3D pose, and the dense graph to estimate the 3D shape. Information in coarse graphs can be propagated over longer distances compared to dense graphs. In addition, information about pose can guide to recover local shape detail and vice versa. We recognize that the connection between coarse and dense is itself a graph, and introduce graph fusion blocks to exchange information between graphs with different scales. We train our model end-to-end and show that we can achieve state-of-the-art results for several evaluation datasets." @default.
- W3206989860 created "2021-10-25" @default.
- W3206989860 creator A5026558988 @default.
- W3206989860 creator A5046694633 @default.
- W3206989860 creator A5066373402 @default.
- W3206989860 date "2021-10-16" @default.
- W3206989860 modified "2023-09-27" @default.
- W3206989860 title "Joint 3D Human Shape Recovery from A Single Imag with Bilayer-Graph." @default.
- W3206989860 cites W1861492603 @default.
- W3206989860 cites W1967554269 @default.
- W3206989860 cites W2080873731 @default.
- W3206989860 cites W2101032778 @default.
- W3206989860 cites W2118931255 @default.
- W3206989860 cites W2135533529 @default.
- W3206989860 cites W2194775991 @default.
- W3206989860 cites W2483862638 @default.
- W3206989860 cites W2573098616 @default.
- W3206989860 cites W2797515701 @default.
- W3206989860 cites W2798637590 @default.
- W3206989860 cites W2883221003 @default.
- W3206989860 cites W2916798096 @default.
- W3206989860 cites W2936102783 @default.
- W3206989860 cites W2936390566 @default.
- W3206989860 cites W2947781663 @default.
- W3206989860 cites W2956061722 @default.
- W3206989860 cites W2962730651 @default.
- W3206989860 cites W2962754033 @default.
- W3206989860 cites W2962778872 @default.
- W3206989860 cites W2963150697 @default.
- W3206989860 cites W2963351448 @default.
- W3206989860 cites W2963907666 @default.
- W3206989860 cites W2963995996 @default.
- W3206989860 cites W2964015378 @default.
- W3206989860 cites W2964062189 @default.
- W3206989860 cites W2964072977 @default.
- W3206989860 cites W2965874802 @default.
- W3206989860 cites W2966735886 @default.
- W3206989860 cites W2969592146 @default.
- W3206989860 cites W2970285700 @default.
- W3206989860 cites W2975420824 @default.
- W3206989860 cites W2979283733 @default.
- W3206989860 cites W2981514602 @default.
- W3206989860 cites W2981978060 @default.
- W3206989860 cites W2982131530 @default.
- W3206989860 cites W2991332406 @default.
- W3206989860 cites W2991621301 @default.
- W3206989860 cites W3035291735 @default.
- W3206989860 cites W3041011810 @default.
- W3206989860 cites W3098612954 @default.
- W3206989860 cites W3108707969 @default.
- W3206989860 cites W3109877674 @default.
- W3206989860 cites W3175199633 @default.
- W3206989860 hasPublicationYear "2021" @default.
- W3206989860 type Work @default.
- W3206989860 sameAs 3206989860 @default.
- W3206989860 citedByCount "0" @default.
- W3206989860 crossrefType "posted-content" @default.
- W3206989860 hasAuthorship W3206989860A5026558988 @default.
- W3206989860 hasAuthorship W3206989860A5046694633 @default.
- W3206989860 hasAuthorship W3206989860A5066373402 @default.
- W3206989860 hasConcept C132525143 @default.
- W3206989860 hasConcept C18819970 @default.
- W3206989860 hasConcept C203776342 @default.
- W3206989860 hasConcept C22149727 @default.
- W3206989860 hasConcept C41008148 @default.
- W3206989860 hasConcept C80444323 @default.
- W3206989860 hasConceptScore W3206989860C132525143 @default.
- W3206989860 hasConceptScore W3206989860C18819970 @default.
- W3206989860 hasConceptScore W3206989860C203776342 @default.
- W3206989860 hasConceptScore W3206989860C22149727 @default.
- W3206989860 hasConceptScore W3206989860C41008148 @default.
- W3206989860 hasConceptScore W3206989860C80444323 @default.
- W3206989860 hasLocation W32069898601 @default.
- W3206989860 hasOpenAccess W3206989860 @default.
- W3206989860 hasPrimaryLocation W32069898601 @default.
- W3206989860 hasRelatedWork W2073806095 @default.
- W3206989860 hasRelatedWork W2489691116 @default.
- W3206989860 hasRelatedWork W2805090752 @default.
- W3206989860 hasRelatedWork W2854384722 @default.
- W3206989860 hasRelatedWork W2891082150 @default.
- W3206989860 hasRelatedWork W2907221513 @default.
- W3206989860 hasRelatedWork W2952832237 @default.
- W3206989860 hasRelatedWork W2954284176 @default.
- W3206989860 hasRelatedWork W2971601118 @default.
- W3206989860 hasRelatedWork W2972933289 @default.
- W3206989860 hasRelatedWork W2981341885 @default.
- W3206989860 hasRelatedWork W2994872218 @default.
- W3206989860 hasRelatedWork W2997001386 @default.
- W3206989860 hasRelatedWork W3012774908 @default.
- W3206989860 hasRelatedWork W3028917156 @default.
- W3206989860 hasRelatedWork W3034116706 @default.
- W3206989860 hasRelatedWork W3123738487 @default.
- W3206989860 hasRelatedWork W3205327953 @default.
- W3206989860 hasRelatedWork W3210522961 @default.
- W3206989860 hasRelatedWork W3213443340 @default.
- W3206989860 isParatext "false" @default.
- W3206989860 isRetracted "false" @default.
- W3206989860 magId "3206989860" @default.
- W3206989860 workType "article" @default.