|
|
The video on the left shows a common sequence where standard SfM methods fail to provide an accurate 3D reconstruction. The subject is performing relevant deformations while the rigid motion is restricted to small pose variations. The amount of deformation in respect to the rigid motion is the cause for the unstable estimates of the 3D shape. In such cases, depth variations could be modelled as deformations.
|
|
|
3D reconstruction without priors: The video shows the 3D reconstructions obtained using a standard procedure to compute deformable 3D shapes from images given the previous video sequence. The results are poor — the method fail to obtain usable information given the degenerate motion. The video shows front, side and top views of the given reconstruction.
|
Adaptation: The video on the left shows a different subject performing only rigid motion. From this sequence it is possible to obtain a rigid 3D shape using standard factorization techniques such as Tomasi&Kanade algorithm. The computed shape is shown in the figure on the left. This shape can be then used to improve the 3D reconstruction even if the subjects’ face have different somatic characteristics. By merging measurements from images and 3D shape prior information we aim to obtained an improved 3D reconstruction.
|
|
3D reconstruction with Adaptation: This is the final 3D reconstruction using the top sequence with the 3D shape prior. Now the depth estimates are reasonably describing the subject’s face and the mouth deformations are properly modelled. In principle this method can deal with any kind of object’s shape: rigid, articulated and deformable.
|
More details in the paper: “A. Del Bue. A Factorization Approach to Structure from Motion with Shape Priors”
-
A. Del Bue, "A factorization approach to structure from motion with shape priors," in Proc. IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska, 2008, pp. 1-8.
@conference{DelBue:2008, title={A factorization approach to structure from motion with shape priors},
author={A. {Del Bue}},
booktitle = {Proc. IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska},
pages={1--8},
year={2008}
}
No Comment.
Add Your Comment