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

arXiv: https://arxiv.org/abs/1903.09233 · HTML: https://mlsanity.com/paper/1903.09233/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Mar 2019.

## Built on by (most cited first, 10 of 10)

- [FlowBench: A Large Scale Benchmark for Flow Simulation over Complex Geometries](https://mlsanity.com/paper/2409.18032/) (2024)
- [A skeletonization algorithm for gradient-based optimization](https://mlsanity.com/paper/2309.02527/) (2023)
- [NURBS-Diff: A Differentiable Programming Module for NURBS](https://mlsanity.com/paper/2104.14547/) (2021)
- [Geometry Matters: Benchmarking Scientific ML Approaches for Flow Prediction around Complex Geometries](https://mlsanity.com/paper/2501.01453/) (2024)
- [Context Attention Network for Skeleton Extraction](https://mlsanity.com/paper/2205.12066/) (2022)
- [Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks](https://mlsanity.com/paper/2310.06437/) (2023)
- [Skelite: Compact Neural Networks for Efficient Iterative Skeletonization](https://mlsanity.com/paper/2503.07369/) (2025)
- [Path Planning using a One-shot-sampling Skeleton Map](https://mlsanity.com/paper/2507.02328/) (2025)
- [Binary Image Skeletonization Using 2-Stage U-Net](https://mlsanity.com/paper/2112.11824/) (2021)
- [Predicting Time-Dependent Flow Over Complex Geometries Using Operator Networks](https://mlsanity.com/paper/2512.04434/) (2025)

## Abstract (arXiv)

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.