Abstract : Most optical flow algorithms provide flow fields as single valued functions of the image sequence domains. Only a very few of them attempt to recover multiple motion vectors at given location, which is necessary when some transparent layers are moving independently. In this report we introduce a novel framework for modeling multivalued motion fields, and propose an energy minimization formulation with smoothing terms and terms implementing velocity model competition. We illustrate the capabilities of this approach on synthetic and real sequences.
https://hal.inria.fr/inria-00077285 Contributor : Rapport de Recherche InriaConnect in order to contact the contributor Submitted on : Tuesday, June 6, 2006 - 10:12:53 AM Last modification on : Thursday, March 17, 2022 - 10:08:32 AM Long-term archiving on: : Monday, September 20, 2010 - 2:35:53 PM
Alonso Ramirez-Manzanares, Mariano Rivera, Pierre Kornprobst, François Lauze. Multi-Valued Motion Fields Estimation for Transparent Sequences with a Variational Approach. [Research Report] RR-5920, INRIA. 2006, pp.25. ⟨inria-00077285v2⟩