Dense Correspondences across Scenes and Scales

Moria Tau, Tal Hassner

نتاج البحث: نشر في مجلةمقالةمراجعة النظراء


We seek a practical method for establishing dense correspondences between two images with similar content, but possibly different 3D scenes. One of the challenges in designing such a system is the local scale differences of objects appearing in the two images. Previous methods often considered only few image pixels; matching only pixels for which stable scales may be reliably estimated. Recently, others have considered dense correspondences, but with substantial costs associated with generating, storing and matching scale invariant descriptors. Our work is motivated by the observation that pixels in the image have contexts - the pixels around them - which may be exploited in order to reliably estimate local scales. We make the following contributions. (i) We show that scales estimated in sparse interest points may be propagated to neighboring pixels where this information cannot be reliably determined. Doing so allows scale invariant descriptors to be extracted anywhere in the image. (ii) We explore three means for propagating this information: using the scales at detected interest points, using the underlying image information to guide scale propagation in each image separately, and using both images together. Finally, (iii), we provide extensive qualitative and quantitative results, demonstrating that scale propagation allows for accurate dense correspondences to be obtained even between very different images, with little computational costs beyond those required by existing methods.

اللغة الأصليةالإنجليزيّة
رقم المقال7229334
الصفحات (من إلى)875-888
عدد الصفحات14
دوريةIEEE Transactions on Pattern Analysis and Machine Intelligence
مستوى الصوت38
رقم الإصدار5
المعرِّفات الرقمية للأشياء
حالة النشرنُشِر - 1 مايو 2016

ملاحظة ببليوغرافية

Publisher Copyright:
© 1979-2012 IEEE.


أدرس بدقة موضوعات البحث “Dense Correspondences across Scenes and Scales'. فهما يشكلان معًا بصمة فريدة.

قم بذكر هذا