Challenge

Competition tracks

We are hosting seven competition tracks in two main domains: The SkelNetOn Challenge (2D) and The ABC Challenge (3D), implemented as independent contests available at Codalab.

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. Now online!



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.
Now online!

Parametric SkelNetOn

Extract a parametric representation of a network of curves of the skeleton and their radii, modeled as a degree-5 BĂ©zier curve in three dimensions. This may be thought of as a regression problem. Now online!


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. Now online!

ABC Geometry Reconstruction Challenges

The ABC Challenge serves as a testbed for common shape analysis and geometry processing tasks. We supplement the challenge with additional software libraries, sets of large-scale standardized benchmarks (data splits, resolutions, and targets), and implementations of evaluation metrics. The first ABC challenge will be hosting a three-track contest on geometry processing, including:

Estimation of non-oriented normals

Predict non-oriented normals from unstructured 3D point clouds. Now online!

Geometric shape segmentation

Segment geometric feature lines from unstructured 3D point clouds or depth images. Now online!

Sharpness fields extraction

Predict a scalar field approximating distance to the closest feature line from unstructured 3D point clouds or depth images. Now online!

Important dates

  • Challenges are open: May, 07, 2021

  • Challenge second phase: July, 22, 2021

  • Challenges close: August 1, 2021

  • Acceptance notification: August 11, 2021

  • Workshop (full day): October 11, 2021