000150660 001__ 150660
000150660 005__ 20190117210906.0
000150660 037__ $$aCONF
000150660 245__ $$aCombining Geometric and Appearance Priors for Robust Homography Estimation
000150660 269__ $$a2010
000150660 260__ $$c2010
000150660 336__ $$aConference Papers
000150660 520__ $$aThe homography between pairs of images are typically computed from the correspondence of keypoints, which are established by using image descriptors. When these descriptors are not reliable, either because of repetitive patterns or large amounts of clutter, additional priors need to be considered. The Blind PnP algorithm makes use of geometric priors to guide the search for matches while computing camera pose. Inspired by this, we propose a novel approach for homography estimation that combines geometric priors with appearance priors of ambiguous descriptors. More specifically, for each point we retain its best candidates according to appearance. We then prune the set of potential matches by iteratively shrinking the regions of the image that are consistent with the geometric prior. We can then successfully compute homographies between pairs of images containing highly repetitive patterns and even under oblique viewing conditions.
000150660 700__ $$aSerradell, Eduard
000150660 700__ $$0242714$$aÖzuysal, Mustafa$$g167953
000150660 700__ $$0240235$$aLepetit, Vincent$$g149007
000150660 700__ $$0240252$$aFua, Pascal$$g112366
000150660 700__ $$aMoreno-Noguer, Francesc
000150660 8564_ $$s555410$$uhttps://infoscience.epfl.ch/record/150660/files/eccv_0780.pdf$$zn/a
000150660 909C0 $$0252087$$pCVLAB$$xU10659
000150660 909CO $$ooai:infoscience.tind.io:150660$$pconf$$pIC
000150660 917Z8 $$x112366
000150660 917Z8 $$x112366
000150660 937__ $$aEPFL-CONF-150660
000150660 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000150660 980__ $$aCONF