Alessio Del Bue Homepage

The figure shows an example of our problem. A 3D shape (b) can be recovered from a rigid image sequence (a) with standard SfM algorithms. The model has now to be registered to a new non-rigid image sequence (c) with 2D trajectories extracted from a subject with different somatic traits. We seek the best registration given both 2D and 3D data which satisfy the metric constraints of the shapes. White dots represent the 2D image data and the red circles our algorithm result.

This problem differs from standard 2D-3D registration problems since we do not have only to estimate for the camera projection, rotation and translation but also for the best 3D shape which adapts to the new 2D measurements. The paper shows a new closed form procedure which can find these parameters which satisfies the metric constraints. The video on the bottom shows results in a face analysis domain.

More details in the paper: “A. Del Bue. Adaptive Metric Registration of 3D Models to Non-rigid Image Trajectories“. Slides for the oral presentation at ECCV 2010 can be found here: PDF (1.85MB)

• 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}
}
  bibtex