Matches in SemOpenAlex for { <https://semopenalex.org/work/W4286769085> ?p ?o ?g. }
Showing items 1 to 65 of
65
with 100 items per page.
- W4286769085 abstract "Fitting parametric models of human bodies, hands or faces to sparse input signals in an accurate, robust, and fast manner has the promise of significantly improving immersion in AR and VR scenarios. A common first step in systems that tackle these problems is to regress the parameters of the parametric model directly from the input data. This approach is fast, robust, and is a good starting point for an iterative minimization algorithm. The latter searches for the minimum of an energy function, typically composed of a data term and priors that encode our knowledge about the problem's structure. While this is undoubtedly a very successful recipe, priors are often hand defined heuristics and finding the right balance between the different terms to achieve high quality results is a non-trivial task. Furthermore, converting and optimizing these systems to run in a performant way requires custom implementations that demand significant time investments from both engineers and domain experts. In this work, we build upon recent advances in learned optimization and propose an update rule inspired by the classic Levenberg-Marquardt algorithm. We show the effectiveness of the proposed neural optimizer on three problems, 3D body estimation from a head-mounted device, 3D body estimation from sparse 2D keypoints and face surface estimation from dense 2D landmarks. Our method can easily be applied to new model fitting problems and offers a competitive alternative to well-tuned 'traditional' model fitting pipelines, both in terms of accuracy and speed." @default.
- W4286769085 created "2022-07-23" @default.
- W4286769085 creator A5007550435 @default.
- W4286769085 creator A5026293522 @default.
- W4286769085 creator A5048464691 @default.
- W4286769085 creator A5069668487 @default.
- W4286769085 date "2021-11-29" @default.
- W4286769085 modified "2023-09-24" @default.
- W4286769085 title "Learning to Fit Morphable Models" @default.
- W4286769085 doi "https://doi.org/10.48550/arxiv.2111.14824" @default.
- W4286769085 hasPublicationYear "2021" @default.
- W4286769085 type Work @default.
- W4286769085 citedByCount "0" @default.
- W4286769085 crossrefType "posted-content" @default.
- W4286769085 hasAuthorship W4286769085A5007550435 @default.
- W4286769085 hasAuthorship W4286769085A5026293522 @default.
- W4286769085 hasAuthorship W4286769085A5048464691 @default.
- W4286769085 hasAuthorship W4286769085A5069668487 @default.
- W4286769085 hasBestOaLocation W42867690851 @default.
- W4286769085 hasConcept C105795698 @default.
- W4286769085 hasConcept C107673813 @default.
- W4286769085 hasConcept C111919701 @default.
- W4286769085 hasConcept C11413529 @default.
- W4286769085 hasConcept C117251300 @default.
- W4286769085 hasConcept C119857082 @default.
- W4286769085 hasConcept C126255220 @default.
- W4286769085 hasConcept C127705205 @default.
- W4286769085 hasConcept C147764199 @default.
- W4286769085 hasConcept C154945302 @default.
- W4286769085 hasConcept C177769412 @default.
- W4286769085 hasConcept C199360897 @default.
- W4286769085 hasConcept C24574437 @default.
- W4286769085 hasConcept C33923547 @default.
- W4286769085 hasConcept C41008148 @default.
- W4286769085 hasConceptScore W4286769085C105795698 @default.
- W4286769085 hasConceptScore W4286769085C107673813 @default.
- W4286769085 hasConceptScore W4286769085C111919701 @default.
- W4286769085 hasConceptScore W4286769085C11413529 @default.
- W4286769085 hasConceptScore W4286769085C117251300 @default.
- W4286769085 hasConceptScore W4286769085C119857082 @default.
- W4286769085 hasConceptScore W4286769085C126255220 @default.
- W4286769085 hasConceptScore W4286769085C127705205 @default.
- W4286769085 hasConceptScore W4286769085C147764199 @default.
- W4286769085 hasConceptScore W4286769085C154945302 @default.
- W4286769085 hasConceptScore W4286769085C177769412 @default.
- W4286769085 hasConceptScore W4286769085C199360897 @default.
- W4286769085 hasConceptScore W4286769085C24574437 @default.
- W4286769085 hasConceptScore W4286769085C33923547 @default.
- W4286769085 hasConceptScore W4286769085C41008148 @default.
- W4286769085 hasLocation W42867690851 @default.
- W4286769085 hasOpenAccess W4286769085 @default.
- W4286769085 hasPrimaryLocation W42867690851 @default.
- W4286769085 hasRelatedWork W1580578212 @default.
- W4286769085 hasRelatedWork W1968714250 @default.
- W4286769085 hasRelatedWork W1989834627 @default.
- W4286769085 hasRelatedWork W2005783716 @default.
- W4286769085 hasRelatedWork W2053923183 @default.
- W4286769085 hasRelatedWork W2058763461 @default.
- W4286769085 hasRelatedWork W2064081561 @default.
- W4286769085 hasRelatedWork W2407281753 @default.
- W4286769085 hasRelatedWork W3125921778 @default.
- W4286769085 hasRelatedWork W3171881916 @default.
- W4286769085 isParatext "false" @default.
- W4286769085 isRetracted "false" @default.
- W4286769085 workType "article" @default.