Template-based Monocular 3D Shape Recovery using Laplacian Meshes
| Autor: | Jonas Ostlund, Pascal Fua, Dat Tien Ngo |
|---|---|
| Předmět: |
FOS: Computer and information sciences
Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Artificial Intelligence Surface 3D reconstruction 0202 electrical engineering electronic engineering information engineering Computer vision Polygon mesh Graphics Mathematics ComputingMethodologies_COMPUTERGRAPHICS Monocular business.industry Applied Mathematics Linear system Deformable Surfaces 020207 software engineering Computational Theory and Mathematics 020201 artificial intelligence & image processing Computer Vision and Pattern Recognition Artificial intelligence business Laplace operator Software Linear least squares Surface reconstruction Curse of dimensionality |
| Zdroj: | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| Popis: | We show that by extending the Laplacian formalism, which was first introduced in the Graphics community to regularize 3D meshes, we can turn the monocular 3D shape reconstruction of a deformable surface given correspondences with a reference image into a much better-posed problem. This allows us to quickly and reliably eliminate outliers by simply solving a linear least squares problem. This yields an initial 3D shape estimate, which is not necessarily accurate, but whose 2D projections are. The initial shape is then refined by a constrained optimization problem to output the final surface reconstruction. Our approach allows us to reduce the dimensionality of the surface reconstruction problem without sacrificing accuracy, thus allowing for real-time implementations. Comment: Article |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|