Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204360318> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W3204360318 endingPage "11614" @default.
- W3204360318 startingPage "11605" @default.
- W3204360318 abstract "This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and typically regress a single estimate for a given input. In contrast to that, in this work, we propose to embrace the reconstruction ambiguity and we recast the problem as learning a mapping from the input to a distribution of plausible 3D poses. Our approach is based on the normalizing flows model and offers a series of advantages. For conventional applications, where a single 3D estimate is required, our formulation allows for efficient mode computation. Using the mode leads to performance that is comparable with the state of the art among deterministic unimodal regression models. Simultaneously, since we have access to the likelihood of each sample, we demonstrate that our model is useful in a series of downstream tasks, where we leverage the probabilistic nature of the prediction as a tool for more accurate estimation. These tasks include reconstruction from multiple uncalibrated views, as well as human model fitting, where our model acts as a powerful image-based prior for mesh recovery. Our results validate the importance of probabilistic modeling, and indicate state-of-the-art performance across a variety of settings. Code and models are available at: this https URL." @default.
- W3204360318 created "2021-10-11" @default.
- W3204360318 creator A5048259380 @default.
- W3204360318 creator A5048438237 @default.
- W3204360318 creator A5050660826 @default.
- W3204360318 creator A5079302923 @default.
- W3204360318 date "2021-08-26" @default.
- W3204360318 modified "2023-10-16" @default.
- W3204360318 title "Probabilistic Modeling for Human Mesh Recovery" @default.
- W3204360318 hasPublicationYear "2021" @default.
- W3204360318 type Work @default.
- W3204360318 sameAs 3204360318 @default.
- W3204360318 citedByCount "1" @default.
- W3204360318 countsByYear W32043603182021 @default.
- W3204360318 crossrefType "proceedings-article" @default.
- W3204360318 hasAuthorship W3204360318A5048259380 @default.
- W3204360318 hasAuthorship W3204360318A5048438237 @default.
- W3204360318 hasAuthorship W3204360318A5050660826 @default.
- W3204360318 hasAuthorship W3204360318A5079302923 @default.
- W3204360318 hasConcept C11413529 @default.
- W3204360318 hasConcept C114289077 @default.
- W3204360318 hasConcept C119857082 @default.
- W3204360318 hasConcept C124101348 @default.
- W3204360318 hasConcept C153083717 @default.
- W3204360318 hasConcept C154945302 @default.
- W3204360318 hasConcept C177264268 @default.
- W3204360318 hasConcept C199360897 @default.
- W3204360318 hasConcept C2776760102 @default.
- W3204360318 hasConcept C2780522230 @default.
- W3204360318 hasConcept C41008148 @default.
- W3204360318 hasConcept C45374587 @default.
- W3204360318 hasConcept C49937458 @default.
- W3204360318 hasConceptScore W3204360318C11413529 @default.
- W3204360318 hasConceptScore W3204360318C114289077 @default.
- W3204360318 hasConceptScore W3204360318C119857082 @default.
- W3204360318 hasConceptScore W3204360318C124101348 @default.
- W3204360318 hasConceptScore W3204360318C153083717 @default.
- W3204360318 hasConceptScore W3204360318C154945302 @default.
- W3204360318 hasConceptScore W3204360318C177264268 @default.
- W3204360318 hasConceptScore W3204360318C199360897 @default.
- W3204360318 hasConceptScore W3204360318C2776760102 @default.
- W3204360318 hasConceptScore W3204360318C2780522230 @default.
- W3204360318 hasConceptScore W3204360318C41008148 @default.
- W3204360318 hasConceptScore W3204360318C45374587 @default.
- W3204360318 hasConceptScore W3204360318C49937458 @default.
- W3204360318 hasLocation W32043603181 @default.
- W3204360318 hasOpenAccess W3204360318 @default.
- W3204360318 hasPrimaryLocation W32043603181 @default.
- W3204360318 hasRelatedWork W1605708294 @default.
- W3204360318 hasRelatedWork W2070379207 @default.
- W3204360318 hasRelatedWork W2317363656 @default.
- W3204360318 hasRelatedWork W2902854273 @default.
- W3204360318 hasRelatedWork W2975401428 @default.
- W3204360318 hasRelatedWork W2976949442 @default.
- W3204360318 hasRelatedWork W2982165393 @default.
- W3204360318 hasRelatedWork W3000633854 @default.
- W3204360318 hasRelatedWork W3009795828 @default.
- W3204360318 hasRelatedWork W3010129597 @default.
- W3204360318 hasRelatedWork W3013266062 @default.
- W3204360318 hasRelatedWork W3047684148 @default.
- W3204360318 hasRelatedWork W3090980445 @default.
- W3204360318 hasRelatedWork W3130158566 @default.
- W3204360318 hasRelatedWork W3141383601 @default.
- W3204360318 hasRelatedWork W3153532599 @default.
- W3204360318 hasRelatedWork W3171806395 @default.
- W3204360318 hasRelatedWork W3193557514 @default.
- W3204360318 hasRelatedWork W3203006492 @default.
- W3204360318 hasRelatedWork W3213531596 @default.
- W3204360318 isParatext "false" @default.
- W3204360318 isRetracted "false" @default.
- W3204360318 magId "3204360318" @default.
- W3204360318 workType "article" @default.