Deviation Magnification: Revealing Departures from Ideal Geometries

(a) Input

(b) Our Result

View 2 (Processed Independently)

(d) Our Result

Revealing the sagging of a house’s roof from a single image. A perfect straight line marked by p₁ and p₂ is automatically fitted to the house’s roof in the input image (a). Our algorithm analyzes and amplifies the geometric deviations from straight, revealing the sagging of the roof in (b). View II shows a consistent result of our method (d) using another image of the same house from a different viewpoint (c). Each viewpoint was processed completely independently.

Abstract

Structures and objects are often supposed to have idealized geome- tries such as straight lines or circles. Although not always visible to the naked eye, in reality, these objects deviate from their idealized models. Our goal is to reveal and visualize such subtle geometric deviations, which can contain useful, surprising information about our world. Our framework, termed Deviation Magnification, takes a still image as input, fits parametric models to objects of interest, computes the geometric deviations, and renders an output image in which the departures from ideal geometries are exaggerated. We demonstrate the correctness and usefulness of our method through quantitative evaluation on a synthetic dataset and by application to challenging natural images.

@article{Wadhwa2015DeviationMagnification,
author = {Neal Wadhwa and Tali Dekel and Donglai Wei and Fr\'{e}do Durand and William T. Freeman},
title = {Deviation Magnification: Revealing Departure from Ideal Geometries},
journal = {ACM Trans. Graph. (Proceedings SIGGRAPH Asia 2015)},
year = {2015},
volume = {34},
number={6}
}

Paper: pdf

SIGGRAPH Asia 2015 Presentation: (zip, 58MB)

Supplemental Video:

Data and Results: Coming Soon!

Acknowledgements

We would like to thank the SIGGRAPH Asia reviewers for their comments. We acknowledge funding support from Shell Research, the Qatar Computing Research Institute, ONR MURI grant N00014-09-1-1051 and NSF grant CGV-1111415.