Re-thinking non-rigid structure from motion
Research output: Contribution to journal › Conference article › Research › peer-review
We present a novel approach to non-rigid structure from motion (NRSFM) from an orthographic video sequence, based on a new interpretation of the problem. Existing approaches assume the object shape space is well-modeled by a linear subspace. Our approach only assumes that small neighborhoods of shapes are well-modeled with a linear subspace. This constrains the shapes to belong to a manifold of dimensionality equal to the number of degrees of freedom of the object. After showing that the problem is still overconstrained, we present a solution composed of a novel initialization algorithm, followed by a robust extension of the Locally Smooth Manifold Learning algorithm tailored to the NRSFM problem. We finally present some test cases where the linear basis method fails (and is actually not meant to work) while the proposed approach is successful.
Original language | English |
---|---|
Journal | 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR |
DOIs | |
Publication status | Published - 2008 |
Externally published | Yes |
Event | 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR - Anchorage, AK, United States Duration: 23 Jun 2008 → 28 Jun 2008 |
Conference
Conference | 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR |
---|---|
Country | United States |
City | Anchorage, AK |
Period | 23/06/2008 → 28/06/2008 |
ID: 302050887