Dense and Accurate Spatio-Temporal Multi-View Stereovision IMAGINE Research Report 09-43
Abstract
In this report, we describe a novel method to simultaneously and accurately estimate the 3D shape and 3D motion of a dynamic scene from multiple-viewpoint calibrated videos. We follow a variational approach in the vein of previous work on stereo reconstruction and scene flow estimation. We adopt a representation of a dynamic scene by an animated mesh, i.e. a polygonal mesh with fixed connectivity whose time-varying vertex positions sample the trajectories of material points. Interestingly, this representation ensures a consistent coding of shape and motion by construction. Our method accurately recovers 3D shape and 3D motion by optimizing the positions of the vertices of the animated mesh. This optimization is driven by an energy function which incorporates multi-view and inter-frame photo-consistency, smoothness of the spatio-temporal surface and of the velocity field. Central to our work is an image-based photo-consistency score which can be efficiently computed and which fully handles projective distortion and partial occlusions. We demonstrate the effectiveness of our method on several challenging real-world dynamic scenes.
Domains
Image Processing [eess.IV]
Fichier principal
IMAGINE_RR-0943.pdf (1.1 Mo)
Télécharger le fichier
README.txt (1.15 Ko)
Télécharger le fichier
dancer_ground_truth_cameras.wmv (118.38 Ko)
Télécharger le fichier
dancer_reconstruction.wmv (246.89 Ko)
Télécharger le fichier
pant_ground_truth_cameras_side_1.wmv (2.67 Mo)
Télécharger le fichier
pant_reconstruction_side_1.wmv (1010.02 Ko)
Télécharger le fichier
pant_reconstruction_side_1_textured.wmv (519.97 Ko)
Télécharger le fichier
pant_reconstruction_side_2.wmv (985.93 Ko)
Télécharger le fichier
Origin : Files produced by the author(s)
Format : Other
Format : Other
Format : Other
Format : Other
Format : Other
Format : Other
Format : Other
Loading...