RepFinder: Finding approximately repeated scene elements for image editing

Ming Ming Cheng, Fang Lue Zhang, Niloy J. Mitra, Xiaolei Huang, Shi Min Hu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Scopus citations

Abstract

Repeated elements are ubiquitous and abundant in both manmade and natural scenes. Editing such images while preserving the repetitions and their relations is nontrivial due to overlap, missing parts, deformation across instances, illumination variation, etc. Manually enforcing such relations is laborious and error-prone. We propose a novel framework where user scribbles are used to guide detection and extraction of such repeated elements. Our detection process, which is based on a novel boundary band method, robustly extracts the repetitions along with their deformations. The algorithm only considers the shape of the elements, and ignores similarity based on color, texture, etc. We then use topological sorting to establish a partial depth ordering of overlapping repeated instances. Missing parts on occluded instances are completed using information from other instances. The extracted repeated instances can then be seamlessly edited and manipulated for a variety of high level tasks that are otherwise difficult to perform. We demonstrate the versatility of our framework on a large set of inputs of varying complexity, showing applications to image rearrangement, edit transfer, deformation propagation, and instance replacement.

Original languageEnglish (US)
Title of host publicationACM SIGGRAPH 2010 Papers, SIGGRAPH 2010
EditorsHugues Hoppe
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9781450302104
DOIs
StatePublished - Jul 26 2010
Event37th International Conference and Exhibition on Computer Graphics and Interactive Techniques, SIGGRAPH 2010 - Los Angeles, United States
Duration: Jul 26 2010Jul 30 2010

Publication series

NameACM SIGGRAPH 2010 Papers, SIGGRAPH 2010

Conference

Conference37th International Conference and Exhibition on Computer Graphics and Interactive Techniques, SIGGRAPH 2010
CountryUnited States
CityLos Angeles
Period7/26/107/30/10

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition
  • Software

Fingerprint Dive into the research topics of 'RepFinder: Finding approximately repeated scene elements for image editing'. Together they form a unique fingerprint.

  • Cite this

    Cheng, M. M., Zhang, F. L., Mitra, N. J., Huang, X., & Hu, S. M. (2010). RepFinder: Finding approximately repeated scene elements for image editing. In H. Hoppe (Ed.), ACM SIGGRAPH 2010 Papers, SIGGRAPH 2010 [83] (ACM SIGGRAPH 2010 Papers, SIGGRAPH 2010). Association for Computing Machinery, Inc. https://doi.org/10.1145/1778765.1778820