The Weizmann Institute of Science
Faculty of Mathematics and Computer Science
Computer Vision Lab



Detecting and Sketching the Common

Shai Bagon, Or Brostovsky, Meirav Galun, Michal Irani

This webpage presents the paper "Detecting and Sketching the Common" (CVPR 2010).
Paper [PDF] [bibtex]
Presentation [PPTX]
Sketching code.
Conference spotlight presentation.


Inputs Output
first input image second input image
third input image output
fourth input image

Abstract

Given very few images containing a common object of interest under severe variations in appearance, we detect the common object and provide a compact visual representation of that object, depicted by a binary sketch. Our algorithm is composed of two stages:
(i) Detect a mutually common (yet non-trivial) ensemble of `self-similarity descriptors' shared by all the input images.
(ii) Having found such a mutually common ensemble, `invert' it to generate a compact sketch which best represents this ensemble.
This provides a simple and compact visual representation of the common object, while eliminating the background clutter of the query images. It can be obtained from very few query images. Such clean sketches may be useful for detection, retrieval, recognition, co-segmentation, and for artistic graphical purposes.

Results

A sample of our qualitative results on a few challenging sets.
More examples can be found in the paper and in the PPTX presentation.

Inputs Output
face 1 face 2 face 3 face 3
face 3 face 3

Inputs Output
input 1 input 2 out put
input 3 input 4

Inputs Output
peace 1 peace 2 peace 3 peace sketch
peace 4 peace 5


Valid HTML 4.01 Transitional Valid CSS
eXTReMe Tracker