2019/03/21 by İlke Demir, Demir, Ilke, Camilla Hahn +17 · 1 citation
Computer Science · Earth and Planetary Sciences · #3D Surveying and Cultural Heritage #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Processing and 3D Reconstruction #Image and Object Detection Techniques
paper · pdf · doi:10.48550/arxiv.1903.09233
openalex publication_date 2019/03/21 · openalex created_date 2020/12/07 · openalex updated_date 2026/07/28
We present SkelNetOn 2019 Challenge and Deep Learning for Geometric Shape\nUnderstanding workshop to utilize existing and develop novel deep learning\narchitectures for shape understanding. We observed that unlike traditional\nsegmentation and detection tasks, geometry understanding is still a new area\nfor deep learning techniques. SkelNetOn aims to bring together researchers from\ndifferent domains to foster learning methods on global shape understanding\ntasks. We aim to improve and evaluate the state-of-the-art shape understanding\napproaches, and to serve as reference benchmarks for future research. Similar\nto other challenges in computer vision, SkelNetOn proposes three datasets and\ncorresponding evaluation methodologies; all coherently bundled in three\ncompetitions with a dedicated workshop co-located with CVPR 2019 conference. In\nthis paper, we describe and analyze characteristics of datasets, define the\nevaluation criteria of the public competitions, and provide baselines for each\ntask.\n