Name
Abstract | ||
|---|---|---|
Recovering the motion of a non-rigid body from a set of monocular images permits the analysis of dynamic scenes in uncontrolled environments. However, the extension of factorisation algorithms for rigid structure from motion to the low-rank non- rigid case has proved challenging. This stems from the comparatively hard problem of finding a linear ``corrective transform'' which recovers the projection and structure matrices from an ambiguous factorisation. We elucidate that this greater difficulty is due to the need to find multiple solutions to a non-trivial problem, casting a number of previous approaches as alleviating this issue by either a) introducing constraints on the basis, making the problems non- identical, or b) incorporating heuristics to encourage a diverse set of solutions, making the problems inter-dependent. While it has previously been recognised that finding a single solution to this problem is sufficient to estimate cameras, we show that it is possible to bootstrap this partial solution to find the complete transform in closed-form. However, we acknowledge that our method minimises an algebraic error and is thus inherently sensitive to deviation from the low-rank model. We compare our closed-form solution for non-rigid structure with known cameras to the closed-form solution of Dai et al.~\cite{Dai2012}, which we find to produce only coplanar reconstructions. We therefore make the recommendation that 3D reconstruction error always be measured relative to a trivial reconstruction such as a planar one. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1109/DICTA.2015.7371247 | 2015 International Conference on Digital Image Computing: Techniques and Applications (DICTA) |
Keywords | Field | DocType |
low-rank nonrigid reconstruction,nonrigid body motion recovery,monocular images,linear corrective transform,projection matrices,structure matrices,coplanar reconstructions,3D reconstruction error | Structure from motion,Iterative reconstruction,Computer vision,Algebraic number,Matrix (mathematics),Computer science,Heuristics,Artificial intelligence,Factorization,Bootstrapping (electronics),3D reconstruction | Conference |
Citations | PageRank | References |
2 | 0.36 | 0 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jack Valmadre | 1 | 466 | 14.08 |
| Sridha Sridharan | 2 | 2092 | 222.69 |
| Simon Denman | 3 | 509 | 56.72 |
| Clinton Fookes | 4 | 743 | 97.41 |
| Simon Lucey | 5 | 2034 | 116.77 |