Deformable surface reconstruction via Riemannian metric preservation

Estimating the pose of an object from a monocular image is a fundamental inverse problem in computer vision. Due to its ill-posed nature, solving this problem requires incorporating deformation priors. In practice, many materials do not perceptibly shrink or extend when manipulated, constituting a r...

ver descrição completa

Detalhes bibliográficos
Autores: Barbany Mayor, Oriol|||0000-0002-1379-9152, Colomé Figueras, Adrià, Torras, Carme|||0000-0002-2933-398X
Formato: artículo
Fecha de publicación:2024
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/416842
Acesso em linha:https://hdl.handle.net/2117/416842
https://dx.doi.org/10.1016/j.cviu.2024.104155
Access Level:acceso abierto
Palavra-chave:Shape-from-template
3Dreconstruction
Deformable surfaces
Differential geometry
Surface parametrization
Àrees temàtiques de la UPC::Informàtica::Infografia
Àrees temàtiques de la UPC::Informàtica::Robòtica
Descrição
Resumo:Estimating the pose of an object from a monocular image is a fundamental inverse problem in computer vision. Due to its ill-posed nature, solving this problem requires incorporating deformation priors. In practice, many materials do not perceptibly shrink or extend when manipulated, constituting a reliable and well-known prior. Mathematically, this translates to the preservation of the Riemannian metric. Neural networks offer the perfect playground to solve the surface reconstruction problem as they can approximate surfaces with arbitrary precision and allow the computation of differential geometry quantities. This paper presents an approach for inferring continuous deformable surfaces from a sequence of images, which is benchmarked against several techniques and achieves state-of-the-art performance without the need for offline training. Being a method that performs per-frame optimization, our method can refine its estimates, contrary to those based on performing a single inference step. Despite enforcing differential geometry constraints at each update, our approach is the fastest of all the tested optimization-based methods.