Palomares, Roberto P.Haro Ortega, GloriaBallester, Coloma2021-03-052021-03-052014Palomares RP, Haro G, Ballester C. A rotation-invariant regularization term for optical flow related problems. In: Cremers D, Reid I, Saito H, Yang MH. Lecture Notes in Computer Science. 12th Asian Conference on Computer Vision (ACCV 2014); 2014 Nov 1-5; Singapore, Singapore. Cham: Springer; 2014. p. 304-19. DOI: 10.1007/978-3-319-16814-2_20http://hdl.handle.net/10230/46667Comunicació presentada al 12th Asian Conference on Computer Vision (ACCV 2014), celebrat de l'1 al 5 de novembre de 2014 a Singapur.This paper proposes a new regularization term for optical flow related problems. The proposed regularizer properly handles rotation movements and it also produces good smoothness conditions on the flow field while preserving discontinuities. We also present a dual formulation of the new term that turns the minimization problem into a saddle-point problem that can be solved using a primal-dual algorithm. The performance of the new regularizer has been compared against the Total Variation (TV) in three different problems: optical flow estimation, optical flow inpainting, and optical flow completion from sparse samples. In the three situations the new regularizer improves the results obtained with the TV as a smoothing term.application/pdfeng© Springer The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-16814-2_20info:eu-repo/semantics/conferenceObjecthttp://dx.doi.org/10.1007/978-3-319-16814-2_20Optical flowProposed regularization termSparse samplingMotion InpaintingGround truth optical flowinfo:eu-repo/semantics/openAccess