Regional Foremost Matching for Internet Scene Images
Publication in refereed journal


Times Cited
Web of Science1WOS source URL (as at 12/01/2022) Click here for the latest count
Altmetrics Information
.

Other information
AbstractWe analyze the dense matching problem for Internet scene images based on the fact that commonly only part of images can be matched due to the variation of view angle, motion, objects, etc. We thus propose regional foremost matching to reject outlier matching points while still producing dense high-quality correspondence in the remaining foremost regions. Our system initializes sparse correspondence, propagates matching with model fitting and optimization, and detects foremost regions robustly. We apply our method to several applications, including time-lapse sequence generation, Internet photo composition, automatic image morphing, and automatic rephotography.
All Author(s) ListXiaoyong Shen, Xin Tao, Chao Zhou, Hongyun Gao, Jiaya Jia
Journal nameACM Transactions on Graphics
Year2016
Month11
Volume Number36
Issue Number6
PublisherAssociation for Computing Machinery (ACM)
Pages178
ISSN0730-0301
eISSN1557-7368
LanguagesEnglish-United States

Last updated on 2022-13-01 at 00:50