TY - GEN
T1 - Synthesizing illumination mosaics from internet photo-collections
AU - Ji, Dinghuang
AU - Dunn, Enrique
AU - Frahm, Jan Michael
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/2/17
Y1 - 2015/2/17
N2 - We propose a framework for the automatic creation of time-lapse mosaics of a given scene. We achieve this by leveraging the illumination variations captured in Internet photo-collections. In order to depict and characterize the illumination spectrum of a scene, our method relies on building discrete representations of the image appearance space through connectivity graphs defined over a pairwise image distance function. The smooth appearance transitions are found as the shortest path in the similarity graph among images, and robust image alignment is achieved by leveraging scene semantics, multi-view geometry, and image warping techniques. The attained results present an insightful and compact visualization of the scene illuminations captured in crowd-sourced imagery.
AB - We propose a framework for the automatic creation of time-lapse mosaics of a given scene. We achieve this by leveraging the illumination variations captured in Internet photo-collections. In order to depict and characterize the illumination spectrum of a scene, our method relies on building discrete representations of the image appearance space through connectivity graphs defined over a pairwise image distance function. The smooth appearance transitions are found as the shortest path in the similarity graph among images, and robust image alignment is achieved by leveraging scene semantics, multi-view geometry, and image warping techniques. The attained results present an insightful and compact visualization of the scene illuminations captured in crowd-sourced imagery.
UR - http://www.scopus.com/inward/record.url?scp=84973870935&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84973870935&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2015.454
DO - 10.1109/ICCV.2015.454
M3 - Conference contribution
AN - SCOPUS:84973870935
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 3988
EP - 3996
BT - 2015 International Conference on Computer Vision, ICCV 2015
T2 - 15th IEEE International Conference on Computer Vision, ICCV 2015
Y2 - 11 December 2015 through 18 December 2015
ER -