Motion Detail Preserving Optical Flow Estimation. Xu, L., Jia, J., & Matsushita, Y. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(9):1744--1757, September, 2012. 00195doi abstract bibtex A common problem of optical flow estimation in the multiscale variational framework is that fine motion structures cannot always be correctly estimated, especially for regions with significant and abrupt displacement variation. A novel extended coarse-to-fine (EC2F) refinement framework is introduced in this paper to address this issue, which reduces the reliance of flow estimates on their initial values propagated from the coarse level and enables recovering many motion details in each scale. The contribution of this paper also includes adaptation of the objective function to handle outliers and development of a new optimization procedure. The effectiveness of our algorithm is demonstrated by Middlebury optical flow benchmarkmarking and by experiments on challenging examples that involve large-displacement motion.
@article{ xu_motion_2012,
title = {Motion {Detail} {Preserving} {Optical} {Flow} {Estimation}},
volume = {34},
issn = {0162-8828},
doi = {10.1109/TPAMI.2011.236},
abstract = {A common problem of optical flow estimation in the multiscale variational framework is that fine motion structures cannot always be correctly estimated, especially for regions with significant and abrupt displacement variation. A novel extended coarse-to-fine (EC2F) refinement framework is introduced in this paper to address this issue, which reduces the reliance of flow estimates on their initial values propagated from the coarse level and enables recovering many motion details in each scale. The contribution of this paper also includes adaptation of the objective function to handle outliers and development of a new optimization procedure. The effectiveness of our algorithm is demonstrated by Middlebury optical flow benchmarkmarking and by experiments on challenging examples that involve large-displacement motion.},
number = {9},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
author = {Xu, Li and Jia, Jiaya and Matsushita, Y.},
month = {September},
year = {2012},
note = {00195},
pages = {1744--1757}
}
Downloads: 0
{"_id":"ucFDsNd4yixDoM3My","bibbaseid":"xu-jia-matsushita-motiondetailpreservingopticalflowestimation-2012","downloads":0,"creationDate":"2015-09-03T07:18:47.120Z","title":"Motion Detail Preserving Optical Flow Estimation","author_short":["Xu, L.","Jia, J.","Matsushita, Y."],"year":2012,"bibtype":"article","biburl":"http://bibbase.org/zotero/fred.qi","bibdata":{"abstract":"A common problem of optical flow estimation in the multiscale variational framework is that fine motion structures cannot always be correctly estimated, especially for regions with significant and abrupt displacement variation. A novel extended coarse-to-fine (EC2F) refinement framework is introduced in this paper to address this issue, which reduces the reliance of flow estimates on their initial values propagated from the coarse level and enables recovering many motion details in each scale. The contribution of this paper also includes adaptation of the objective function to handle outliers and development of a new optimization procedure. The effectiveness of our algorithm is demonstrated by Middlebury optical flow benchmarkmarking and by experiments on challenging examples that involve large-displacement motion.","author":["Xu, Li","Jia, Jiaya","Matsushita, Y."],"author_short":["Xu, L.","Jia, J.","Matsushita, Y."],"bibtex":"@article{ xu_motion_2012,\n title = {Motion {Detail} {Preserving} {Optical} {Flow} {Estimation}},\n volume = {34},\n issn = {0162-8828},\n doi = {10.1109/TPAMI.2011.236},\n abstract = {A common problem of optical flow estimation in the multiscale variational framework is that fine motion structures cannot always be correctly estimated, especially for regions with significant and abrupt displacement variation. A novel extended coarse-to-fine (EC2F) refinement framework is introduced in this paper to address this issue, which reduces the reliance of flow estimates on their initial values propagated from the coarse level and enables recovering many motion details in each scale. The contribution of this paper also includes adaptation of the objective function to handle outliers and development of a new optimization procedure. The effectiveness of our algorithm is demonstrated by Middlebury optical flow benchmarkmarking and by experiments on challenging examples that involve large-displacement motion.},\n number = {9},\n journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},\n author = {Xu, Li and Jia, Jiaya and Matsushita, Y.},\n month = {September},\n year = {2012},\n note = {00195},\n pages = {1744--1757}\n}","bibtype":"article","doi":"10.1109/TPAMI.2011.236","id":"xu_motion_2012","issn":"0162-8828","journal":"IEEE Transactions on Pattern Analysis and Machine Intelligence","key":"xu_motion_2012","month":"September","note":"00195","number":"9","pages":"1744--1757","title":"Motion Detail Preserving Optical Flow Estimation","type":"article","volume":"34","year":"2012","bibbaseid":"xu-jia-matsushita-motiondetailpreservingopticalflowestimation-2012","role":"author","urls":{},"downloads":0},"search_terms":["motion","detail","preserving","optical","flow","estimation","xu","jia","matsushita"],"keywords":[],"authorIDs":[],"dataSources":["y8en6y5RHukfeLuPH"]}