Matches in SemOpenAlex for { <https://semopenalex.org/work/W2943990982> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2943990982 abstract "This paper addresses the problem of 3D human pose and shape estimation from a single image. Previous approaches consider a parametric model of the human body, SMPL, and attempt to regress the model parameters that give rise to a mesh consistent with image evidence. This parameter regression has been a very challenging task, with model-based approaches underperforming compared to nonparametric solutions in terms of pose estimation. In our work, we propose to relax this heavy reliance on the model's parameter space. We still retain the topology of the SMPL template mesh, but instead of predicting model parameters, we directly regress the 3D location of the mesh vertices. This is a heavy task for a typical network, but our key insight is that the regression becomes significantly easier using a Graph-CNN. This architecture allows us to explicitly encode the template mesh structure within the network and leverage the spatial locality the mesh has to offer. Image-based features are attached to the mesh vertices and the Graph-CNN is responsible to process them on the mesh structure, while the regression target for each vertex is its 3D location. Having recovered the complete 3D geometry of the mesh, if we still require a specific model parametrization, this can be reliably regressed from the vertices locations. We demonstrate the flexibility and the effectiveness of our proposed graph-based mesh regression by attaching different types of features on the mesh vertices. In all cases, we outperform the comparable baselines relying on model parameter regression, while we also achieve state-of-the-art results among model-based pose estimation approaches." @default.
- W2943990982 created "2019-05-16" @default.
- W2943990982 creator A5048259380 @default.
- W2943990982 creator A5048438237 @default.
- W2943990982 creator A5050660826 @default.
- W2943990982 date "2019-05-08" @default.
- W2943990982 modified "2023-09-27" @default.
- W2943990982 title "Convolutional Mesh Regression for Single-Image Human Shape Reconstruction" @default.
- W2943990982 hasPublicationYear "2019" @default.
- W2943990982 type Work @default.
- W2943990982 sameAs 2943990982 @default.
- W2943990982 citedByCount "0" @default.
- W2943990982 crossrefType "posted-content" @default.
- W2943990982 hasAuthorship W2943990982A5048259380 @default.
- W2943990982 hasAuthorship W2943990982A5048438237 @default.
- W2943990982 hasAuthorship W2943990982A5050660826 @default.
- W2943990982 hasConcept C104317684 @default.
- W2943990982 hasConcept C105795698 @default.
- W2943990982 hasConcept C11413529 @default.
- W2943990982 hasConcept C114614502 @default.
- W2943990982 hasConcept C117251300 @default.
- W2943990982 hasConcept C121684516 @default.
- W2943990982 hasConcept C132525143 @default.
- W2943990982 hasConcept C153083717 @default.
- W2943990982 hasConcept C153180895 @default.
- W2943990982 hasConcept C154945302 @default.
- W2943990982 hasConcept C184720557 @default.
- W2943990982 hasConcept C185592680 @default.
- W2943990982 hasConcept C194401833 @default.
- W2943990982 hasConcept C31487907 @default.
- W2943990982 hasConcept C33923547 @default.
- W2943990982 hasConcept C41008148 @default.
- W2943990982 hasConcept C55493867 @default.
- W2943990982 hasConcept C66746571 @default.
- W2943990982 hasConcept C80444323 @default.
- W2943990982 hasConcept C80899671 @default.
- W2943990982 hasConcept C83546350 @default.
- W2943990982 hasConceptScore W2943990982C104317684 @default.
- W2943990982 hasConceptScore W2943990982C105795698 @default.
- W2943990982 hasConceptScore W2943990982C11413529 @default.
- W2943990982 hasConceptScore W2943990982C114614502 @default.
- W2943990982 hasConceptScore W2943990982C117251300 @default.
- W2943990982 hasConceptScore W2943990982C121684516 @default.
- W2943990982 hasConceptScore W2943990982C132525143 @default.
- W2943990982 hasConceptScore W2943990982C153083717 @default.
- W2943990982 hasConceptScore W2943990982C153180895 @default.
- W2943990982 hasConceptScore W2943990982C154945302 @default.
- W2943990982 hasConceptScore W2943990982C184720557 @default.
- W2943990982 hasConceptScore W2943990982C185592680 @default.
- W2943990982 hasConceptScore W2943990982C194401833 @default.
- W2943990982 hasConceptScore W2943990982C31487907 @default.
- W2943990982 hasConceptScore W2943990982C33923547 @default.
- W2943990982 hasConceptScore W2943990982C41008148 @default.
- W2943990982 hasConceptScore W2943990982C55493867 @default.
- W2943990982 hasConceptScore W2943990982C66746571 @default.
- W2943990982 hasConceptScore W2943990982C80444323 @default.
- W2943990982 hasConceptScore W2943990982C80899671 @default.
- W2943990982 hasConceptScore W2943990982C83546350 @default.
- W2943990982 hasLocation W29439909821 @default.
- W2943990982 hasOpenAccess W2943990982 @default.
- W2943990982 hasPrimaryLocation W29439909821 @default.
- W2943990982 hasRelatedWork W1574406957 @default.
- W2943990982 hasRelatedWork W1597534740 @default.
- W2943990982 hasRelatedWork W2089123523 @default.
- W2943990982 hasRelatedWork W2401137510 @default.
- W2943990982 hasRelatedWork W2543959933 @default.
- W2943990982 hasRelatedWork W2626517218 @default.
- W2943990982 hasRelatedWork W2767962252 @default.
- W2943990982 hasRelatedWork W2809201693 @default.
- W2943990982 hasRelatedWork W2952728049 @default.
- W2943990982 hasRelatedWork W2964090155 @default.
- W2943990982 hasRelatedWork W2971210400 @default.
- W2943990982 hasRelatedWork W2995334918 @default.
- W2943990982 hasRelatedWork W2998122921 @default.
- W2943990982 hasRelatedWork W3002662895 @default.
- W2943990982 hasRelatedWork W3006015622 @default.
- W2943990982 hasRelatedWork W3039744162 @default.
- W2943990982 hasRelatedWork W3043851655 @default.
- W2943990982 hasRelatedWork W3044063956 @default.
- W2943990982 hasRelatedWork W3166798139 @default.
- W2943990982 hasRelatedWork W3174238309 @default.
- W2943990982 isParatext "false" @default.
- W2943990982 isRetracted "false" @default.
- W2943990982 magId "2943990982" @default.
- W2943990982 workType "article" @default.