Neural best-buddies: Sparse cross-domain correspondence

Kfir Aberman*, Jing Liao, Mingyi Shi, Dani Lischinski, Baoquan Chen, Daniel Cohen-Or

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

63 Scopus citations

Abstract

Correspondence between images is a fundamental problem in computer vision, with a variety of graphics applications. This paper presents a novel method for sparse cross-domain correspondence. Our method is designed for pairs of images where the main objects of interest may belong to different semantic categories and differ drastically in shape and appearance, yet still contain semantically related or geometrically similar parts. Our approach operates on hierarchies of deep features, extracted from the input images by a pre-trained CNN. Specifically, starting from the coarsest layer in both hierarchies, we search for Neural Best Buddies (NBB): Pairs of neurons that are mutual nearest neighbors. The key idea is then to percolate NBBs through the hierarchy, while narrowing down the search regions at each level and retaining only NBBs with significant activations. Furthermore, in order to overcome differences in appearance, each pair of search regions is transformed into a common appearance. We evaluate our method via a user study, in addition to comparisons with alternative correspondence approaches. The usefulness of our method is demonstrated using a variety of graphics applications, including crossdomain image alignment, creation of hybrid images, automatic image morphing, and more.

Original languageAmerican English
Article numberA30
JournalACM Transactions on Graphics
Volume37
Issue number4
DOIs
StatePublished - 2018

Bibliographical note

Publisher Copyright:
© 2018 Association for Computing Machinery.

Keywords

  • cross-domain correspondence
  • image hybrids
  • image morphing

Fingerprint

Dive into the research topics of 'Neural best-buddies: Sparse cross-domain correspondence'. Together they form a unique fingerprint.

Cite this