TY - JOUR
T1 - Coherency Sensitive Hashing
AU - Korman, Simon
AU - Avidan, Shai
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2016/6/1
Y1 - 2016/6/1
N2 - Coherency Sensitive Hashing (CSH) extends Locality Sensitivity Hashing (LSH) and PatchMatch to quickly find matching patches between two images. LSH relies on hashing, which maps similar patches to the same bin, in order to find matching patches. PatchMatch, on the other hand, relies on the observation that images are coherent, to propagate good matches to their neighbors in the image plane, using random patch assignment to seed the initial matching. CSH relies on hashing to seed the initial patch matching and on image coherence to propagate good matches. In addition, hashing lets it propagate information between patches with similar appearance (i.e., map to the same bin). This way, information is propagated much faster because it can use similarity in appearance space or neighborhood in the image plane. As a result, CSH is at least three to four times faster than PatchMatch and more accurate, especially in textured regions, where reconstruction artifacts are most noticeable to the human eye. We verified CSH on a new, large scale, data set of 133 image pairs and experimented on several extensions, including: k nearest neighbor search, the addition of rotation and matching three dimensional patches in videos.
AB - Coherency Sensitive Hashing (CSH) extends Locality Sensitivity Hashing (LSH) and PatchMatch to quickly find matching patches between two images. LSH relies on hashing, which maps similar patches to the same bin, in order to find matching patches. PatchMatch, on the other hand, relies on the observation that images are coherent, to propagate good matches to their neighbors in the image plane, using random patch assignment to seed the initial matching. CSH relies on hashing to seed the initial patch matching and on image coherence to propagate good matches. In addition, hashing lets it propagate information between patches with similar appearance (i.e., map to the same bin). This way, information is propagated much faster because it can use similarity in appearance space or neighborhood in the image plane. As a result, CSH is at least three to four times faster than PatchMatch and more accurate, especially in textured regions, where reconstruction artifacts are most noticeable to the human eye. We verified CSH on a new, large scale, data set of 133 image pairs and experimented on several extensions, including: k nearest neighbor search, the addition of rotation and matching three dimensional patches in videos.
KW - Image Matching
KW - Nearest Neighbor Fields
KW - Patch Matching
KW - Video Matching
UR - http://www.scopus.com/inward/record.url?scp=84969753090&partnerID=8YFLogxK
U2 - 10.1109/TPAMI.2015.2477814
DO - 10.1109/TPAMI.2015.2477814
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:84969753090
SN - 0162-8828
VL - 38
SP - 1099
EP - 1112
JO - IEEE Transactions on Pattern Analysis and Machine Intelligence
JF - IEEE Transactions on Pattern Analysis and Machine Intelligence
IS - 6
M1 - 7254191
ER -