Challenge

Competition tracks

We are hosting four competition tracks in The SkelNetOn Challenge (2D) available now at Codalab (See below for links to each individual challenge)! 

Awards 

The winning submission in each seven track will receive a prize (either cash or equipment) provided by the workshop sponsors. The top submissions in each category with accepted papers in the workshop will be chosen as finalists and will be invited to present their research in the spotlight session. 

SkelNetOn Challenges

The SkelNetOn Challenge is structured around shape understanding in four domains. We provide shape datasets and some complementary resources (e.g, pre/post-processing, sampling, and data augmentation scripts) and the testing platform. Submissions to the challenge will perform one of the following tasks:

Pixel SkelNetOn

Extract skeleton pixels from a binary shape image. This is a binary classification problem where image pixels are labeled as on or off the skeleton. The challenge is live here!


Point SkelNetOn

Extract skeleton points from a shape point cloud. This may be treated as a binary classification problem where points are labeled as on or off the skeleton, though other formulations are acceptable. The challenge is live here!

Parametric SkelNetOn

Extract a parametric representation of a network of curves of the skeleton and their radii, modeled as a degree-5 Bézier curve in three dimensions. This may be thought of as a regression problem. The challenge is live here!

Image SkelNetOn

Extract skeleton pixels from RGB images. This may be thought of as a superset of the first track, or as a recognition problem. The challenge is live here!

Important dates