Nautilus: recovering regional symmetry transformations for image editing

Michal Lukác, Daniel Sýkora, Kalyan Sunkavalli, Eli Shechtman, Ondrej Jamriska, Nathan Carr, Tomás PajdlaACM Trans. Graphics 2017 · OpenReview

Abstract

Natural images often exhibit symmetries that should be taken into account when editing them. In this paper we present Nautilus --- a method for automatically identifying symmetric regions in an image along with their corresponding symmetry transformations. We compute dense local similarity symmetry transformations using a novel variant of the Generalised PatchMatch algorithm that uses Metropolis-Hastings sampling. We combine and refine these local symmetries using an extended Lucas-Kanade algorithm to compute regional transformations and their spatial extents. Our approach produces dense estimates of complex symmetries that are combinations of translation, rotation, scale, and reflection under perspective distortion. This enables a number of automatic symmetry-aware image editing applications including inpainting, rectification, beautification, and segmentation, and we demonstrate state-of-the-art applications for each of them.
BibTeX
@article{lukac2017nautilus,
  author = {Michal Lukác and Daniel Sýkora and Kalyan Sunkavalli and Eli Shechtman and Ondrej Jamriska and Nathan Carr and Tomás Pajdla},
  title = {{Nautilus: recovering regional symmetry transformations for image editing}},
  journal = {ACM Trans. Graphics},
  year = {2017},
  url = {https://openreview.net/forum?id=9MlVVzpFaW},
}

Loading related content...

Figure