de.mpg.escidoc.pubman.appbase.FacesBean
Deutsch
 
Hilfe Wegweiser Datenschutzhinweis Impressum Kontakt
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT

Freigegeben

Konferenzbeitrag

NRSfM using Local Rigidity

MPG-Autoren
http://pubman.mpdl.mpg.de/cone/persons/resource/persons140740

Akhter,  Ijaz
Dept. Perceiving Systems, Max Planck Institute for Intelligent Systems, Max Planck Society;

Externe Ressourcen
Es sind keine Externen Ressourcen verfügbar
Volltexte (frei zugänglich)
Es sind keine frei zugänglichen Volltexte verfügbar
Ergänzendes Material (frei zugänglich)
Es sind keine frei zugänglichen Ergänzenden Materialien verfügbar
Zitation

Rehan, A., Zaheer, A., Akhter, I., Saeed, A., Mahmood, B., Usmani, M., et al. (2014). NRSfM using Local Rigidity. In Proceedings Winter Conference on Applications of Computer Vision (pp. 69-74). Steamboat Springs, CO, USA: IEEE. doi:10.1109/WACV.2014.6836116.


Zitierlink: http://hdl.handle.net/11858/00-001M-0000-0025-B997-2
Zusammenfassung
Factorization methods for computation of nonrigid structure have limited practicality, and work well only when there is large enough camera motion between frames, with long sequences and limited or no occlusions. We show that typical nonrigid structure can often be approximated well as locally rigid sub-structures in time and space. Specifically, we assume that: 1) the structure can be approximated as rigid in a short local time window and 2) some point pairs stay relatively rigid in space, maintaining a fixed distance between them during the sequence. We first use the triangulation constraints in rigid SFM over a sliding time window to get an initial estimate of the nonrigid 3D structure. We then automatically identify relatively rigid point pairs in this structure, and use their length-constancy simultaneously with triangulation constraints to refine the structure estimate. Unlike factorization methods, the structure is estimated independent of the camera motion computation, adding to the simplicity and stability of the approach. Further, local factorization inherently handles significant natural occlusions gracefully, performing much better than the state-of-the art. We show more stable and accurate results as compared to the state-of-the art on even short sequences starting from 15 frames only, containing camera rotations as small as 2 degree and up to 50 percent missing data.