Embedded Files
Why:
Why:
Regular or near-regular forms are commonplace in our surroundings as well as in micro- and macro-scaled worlds from molecules to galaxies. Discovery of such forms directly impacts our recognition, perception and (re)action in the real world. A recent survey indicates that in this critical aspect of cross-domain, cross-scale perception, computer vision is still largely behind human and animal vision, especially in robust real world near-regular pattern recognition.
What:
What:
In this workshop, we focus on the computational symmetry aspect through a series of challenges in which competitors submit algorithms for detecting different types of symmetry in natural scenes, i.e., detecting "symmetry in the wild". We also invite various papers representing a number of tasks for which symmetry can play a critical role, including image/video editing, saliency/attention, 3D reconstruction, object recognition and segmentation, scene categorization, and urban scene parsing.
Symmetry challenges:
Symmetry challenges:
From 2D Datasets:
- Reflection
- Rotation
- Translation 1D (frieze)
- Translation 2D (wallpaper)
- Medial axis
From 3D Datasets:
- Global reflection symmetry (synthetic data)
- Local reflection symmetry (synthetic data)
- Global reflection symmetry (real data)
- Local reflection symmetry (real data)
News
News
- Deadline for challenge and paper submissions extended until
July 24August 7! - The test images for the Medial axis/skeleton detection challenge have been released! Download the updated datasets.
- The submission instructions have been updated. We now ask for a 4-page report for works that have been published already. Check the Submission page for more information.
- We have created a poster for this challenge [link]. Please help us get the word out by placing this at conferences and wherever it will spread the word.
Dates:
Dates:
Training Sets Released: May 15
Submission Deadline: July 17 July 24 August 7
Decisions Made: August 18
Camera-Ready: August 24
Workshop Date: October 28
Workshop Date: October 28
Keynote Speakers:
Keynote Speakers:
Alan Yuille
Alan Yuille
Bloomberg Distinghuished Professor of Cognitive Science and Computer Science
Johns Hopkins University
Johns Hopkins University
Zygmunt Pizlo
Zygmunt Pizlo
Professor and Endowed Chair in Mathematical Psychology Department of Cognitive Sciences
University of California at Irvine
University of California at Irvine
Sponsors
Sponsors
Want to sponsor?
Want to sponsor?
If you would like to sponsor this competition, please email Prof. Yanxi Liu at:
yanxi AT cse.psu.edu
Google Sites
Report abuse