# SkelNetOn 2019: Dataset and Challenge on Deep Learning for Geometric Shape Understanding

## TL;DR

SkelNetOn 2019 introduced datasets, benchmarks, and a challenge to advance deep learning methods for geometric shape understanding, a relatively new area distinct from traditional segmentation and detection tasks.

## Contribution

The paper presents the SkelNetOn 2019 challenge, including datasets, evaluation criteria, and baseline results, to foster research in deep learning for global shape understanding.

## Key findings

- Three datasets for shape understanding tasks
- Evaluation methodologies for shape recognition
- Baseline results for each task

## Abstract

We present SkelNetOn 2019 Challenge and Deep Learning for Geometric Shape Understanding workshop to utilize existing and develop novel deep learning architectures for shape understanding. We observed that unlike traditional segmentation and detection tasks, geometry understanding is still a new area for deep learning techniques. SkelNetOn aims to bring together researchers from different domains to foster learning methods on global shape understanding tasks. We aim to improve and evaluate the state-of-the-art shape understanding approaches, and to serve as reference benchmarks for future research. Similar to other challenges in computer vision, SkelNetOn proposes three datasets and corresponding evaluation methodologies; all coherently bundled in three competitions with a dedicated workshop co-located with CVPR 2019 conference. In this paper, we describe and analyze characteristics of datasets, define the evaluation criteria of the public competitions, and provide baselines for each task.