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.
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.
From 2D Datasets:
From 3D Datasets:
Training Sets Released: May 15
Submission Deadline: July 17 July 24 August 7
Decisions Made: August 18
Camera-Ready: August 24