2D Cross-View Object Segmentation and Perceptual Grouping in Computer-Aided Design Drawings

Mohamed Dhia Elhak Besbes, Zahra Vahidi Ferdousi, Hedi Tabia, Mouna Fradi; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2023, pp. 1745-1754

Abstract

This paper introduces our methods in creating a comprehensive evaluation resource for assessing the capabilities of algorithms aimed at segmenting and perceptually grouping 2D mechanical technical drawings. Our dataset encompasses a diverse collection of such drawings, accompanied by semi-automated annotations of segments and groups. These annotations were reviewed by domain experts, following detailed guidelines to ensure both consistency and top-notch quality. The dataset is intended to serve as an invaluable asset for researchers dedicated to advancing techniques that enhance the comprehension and interpretation of 2D mechanical drawings.

Related Material

[pdf]
[bibtex]
@InProceedings{Besbes_2023_ICCV, author = {Besbes, Mohamed Dhia Elhak and Ferdousi, Zahra Vahidi and Tabia, Hedi and Fradi, Mouna}, title = {2D Cross-View Object Segmentation and Perceptual Grouping in Computer-Aided Design Drawings}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2023}, pages = {1745-1754} }