This Article 
 Bibliographic References 
 Add to: 
Stochastic Exploration of Ambiguities for Nonrigid Shape Recovery
Feb. 2013 (vol. 35 no. 2)
pp. 463-475
F. Moreno-Noguer, Inst. de Robot. i Inf. Ind., UPC, Barcelona, Spain
P. Fua, Comput. Vision Lab., EPFL, Lausanne, Switzerland
Recovering the 3D shape of deformable surfaces from single images is known to be a highly ambiguous problem because many different shapes may have very similar projections. This is commonly addressed by restricting the set of possible shapes to linear combinations of deformation modes and by imposing additional geometric constraints. Unfortunately, because image measurements are noisy, such constraints do not always guarantee that the correct shape will be recovered. To overcome this limitation, we introduce a stochastic sampling approach to efficiently explore the set of solutions of an objective function based on point correspondences. This allows us to propose a small set of ambiguous candidate 3D shapes and then use additional image information to choose the best one. As a proof of concept, we use either motion or shading cues to this end and show that we can handle a complex objective function without having to solve a difficult nonlinear minimization problem. The advantages of our method are demonstrated on a variety of problems including both real and synthetic data.
Index Terms:
stochastic processes,computational geometry,image reconstruction,image sampling,minimisation,solid modelling,nonlinear minimization problem,stochastic ambiguity exploration,nonrigid shape recovery,3D shape,deformable surfaces,deformation modes,geometric constraints,image measurements,stochastic sampling approach,objective function,point correspondences,Shape,Three dimensional displays,Image reconstruction,Space exploration,Covariance matrix,Light sources,Deformable models,monocular shape estimation,Deformable surfaces
F. Moreno-Noguer, P. Fua, "Stochastic Exploration of Ambiguities for Nonrigid Shape Recovery," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 2, pp. 463-475, Feb. 2013, doi:10.1109/TPAMI.2012.102
Usage of this product signifies your acceptance of the Terms of Use.