DUA: A Domain-Unified Approach for Cross-Dataset 3D Human Pose Estimation

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorUniversity of Florence-
Autor(es): dc.creatorManesco, João Renato Ribeiro-
Autor(es): dc.creatorBerretti, Stefano-
Autor(es): dc.creatorMarana, Aparecido Nilceu-
Data de aceite: dc.date.accessioned2025-08-21T22:35:43Z-
Data de disponibilização: dc.date.available2025-08-21T22:35:43Z-
Data de envio: dc.date.issued2025-04-29-
Data de envio: dc.date.issued2023-09-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.3390/s23177312-
Fonte completa do material: dc.identifierhttps://hdl.handle.net/11449/306784-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/306784-
Descrição: dc.descriptionHuman pose estimation is an important Computer Vision problem, whose goal is to estimate the human body through joints. Currently, methods that employ deep learning techniques excel in the task of 2D human pose estimation. However, the use of 3D poses can bring more accurate and robust results. Since 3D pose labels can only be acquired in restricted scenarios, fully convolutional methods tend to perform poorly on the task. One strategy to solve this problem is to use 2D pose estimators, to estimate 3D poses in two steps using 2D pose inputs. Due to database acquisition constraints, the performance improvement of this strategy can only be observed in controlled environments, therefore domain adaptation techniques can be used to increase the generalization capability of the system by inserting information from synthetic domains. In this work, we propose a novel method called Domain Unified approach, aimed at solving pose misalignment problems on a cross-dataset scenario, through a combination of three modules on top of the pose estimator: pose converter, uncertainty estimator, and domain classifier. Our method led to a 44.1mm (29.24%) error reduction, when training with the SURREAL synthetic dataset and evaluating with Human3.6M over a no-adaption scenario, achieving state-of-the-art performance.-
Descrição: dc.descriptionFaculty of Sciences UNESP—São Paulo State University, SP-
Descrição: dc.descriptionMedia Integration and Communication Center (MICC) University of Florence-
Descrição: dc.descriptionFaculty of Sciences UNESP—São Paulo State University, SP-
Idioma: dc.languageen-
Relação: dc.relationSensors-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subject3D human pose estimation-
Palavras-chave: dc.subjectadversarial neural networks-
Palavras-chave: dc.subjectdomain adaptation-
Título: dc.titleDUA: A Domain-Unified Approach for Cross-Dataset 3D Human Pose Estimation-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.