2026-04-17T07:39:20Zhttps://recercat.cat/oai/request

oai:recercat.cat:10230/358222025-12-21T18:05:19Zcom_2072_6col_2072_452952

00925njm 22002777a 4500 dc Oliver, Maria author Palomares, Roberto P. author Ballester, Coloma author Haro Ortega, Gloria author 2018-11-22T08:57:53Z 2018-11-22T08:57:53Z 2017 Comunicació presentada al congrés IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) celebrat del 5 al 9 de març a Nova Orleans (EUA). We propose a new variational method for the completion of moving shapes through binary video inpainting that works by smoothly recovering the objects into an inpainting hole. We solve it by a simple dynamic shape analysis algorithm based on threshold dynamics. The model takes into account the optical flow and motion occlusions. The resulting inpainting algorithm diffuses the available information along the space and the visible trajectories of the pixels in time. We show its performance with examples from the Sintel dataset, which contains complex object motion and occlusions. Shape completion Binary video inpainting Threshold dynamics Spatio-temporal binary video inpainting via threshold dynamics