Adaptive Structure from Motion and Registration
Partially supported by Pourtugese FCT grant MODI-PTDC/EEA ACR/72201/2006.
-
A. Del Bue, "Adaptive Non-rigid Registration and Structure from Motion from Image Trajectories," International Journal of Computer Vision, vol. 103, pp. 226-239, 2013.
@article {DelBue:IJCV2013,
author = {Del Bue, Alessio},
year={2013},
affiliation = {Pattern Analysis and Computer Vision (PAVIS), Istituto Italiano di Tecnologia (IIT), Via Morego 30, 16163 Genova, Italy},
title = {Adaptive Non-rigid Registration and Structure from Motion from Image Trajectories},
journal = {International Journal of Computer Vision},
publisher = {Springer Netherlands},
issn = {0920-5691},
volume = {103},
issue = {2},
pages = {226-239},
month = {June},
url = {http://dx.doi.org/10.1007/s11263-012-0577-9}
}
Problem Statement:
The problem is to compute a 3D reconstruction and registration from sequences which can be adapted whenever we have a guess of the shape to reconstruct/register. The Adaptive Structure from Motion framework finds a joint description between the data provided by the user and the measured data from the images. This new approach can deliver good results in two specific problems: Non-rigid Structure from Motion with degenerate image sequences and Adaptive 3D registration to image trajectories.
|
Adaptive 2D-3D registration
|
This work addresses the problem of registering a 3D model, represented as a cloud of points lying over a surface, to a set of 2D deforming image trajectories in the image plane. The proposed approach can adapt to a scenario where the 3D model to register is not an exact description of the measured image data. This results in finding the best 2D–3D registration, given the complexity of having both 2D deforming data and a coarse description of the image observations. Check this dedicated web page for details.
|
-
A. Del Bue, "Adaptive Metric Registration of 3D Models to Non-rigid Image Trajectories," in 11th European Conference on Computer Vision (ECCV 2010), Crete, Greece, 2010, pp. 87-100.
@inproceedings{DelBue:2010,
author = {A. {Del Bue}},
title = {Adaptive Metric Registration of 3D Models to Non-rigid Image Trajectories},
editor = {Kostas Daniilidis and Petros Maragos and Nikos Paragios},
booktitle = {11th European Conference on Computer Vision (ECCV 2010), Crete, Greece},
publisher = {Springer},
location = {Heidelberg},
series = {Lecture Notes in Computer Science},
volume = {6313},
year = {2010},
isbn = {978-3-642-15557-4},
pages = {87--100}
}
Adaptive Structure from Motion
|
This work presents an approach for including 3D prior models into a factorization framework for structure from motion. The proposed method computes a closed-form affine fit which mixes the information from the data and the 3D prior using GSVD. Moreover, it is general in regards to different classes of objects treated: rigid, articulated and deformable. The inclusion of the shape prior may aid the inference of camera motion and 3D structure components whenever the data is degenerate (i.e. nearly planar motion). Check this dedicated web page for details.
|
-
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}
}
[...] Adaptive SfM [...]