Citing:@article{2022-def,
abstract = {We propose Deep Estimators of Features (DEFs), a learning-based framework for predicting sharp geometric features in sampled 3D shapes. Differently from existing data-driven methods, which reduce this problem to feature classification, we propose to regress a scalar field representing the distance from point samples to the closest feature line on local patches. Our approach is the first that scales to massive point clouds by fusing distance-to-feature estimates obtained on individual patches.We extensively evaluate our approach against related state-of-the-art methods on newly proposed synthetic and real-world 3D CAD model benchmarks. Our approach not only outperforms these (with improvements in Recall and False Positives Rates), but generalizes to real-world scans after training our model on synthetic data and fine-tuning it on a small dataset of scanned data.We demonstrate a downstream application, where we reconstruct an explicit representation of straight and curved sharp feature lines from range scan data.We make code, pre-trained models, and our training and evaluation datasets available at https://github.com/artonson/def.},
address = {New York, NY, USA},
articleno = {108},
author = {Matveev, Albert and Rakhimov, Ruslan and Artemov, Alexey and Bobrovskikh, Gleb and Egiazarian, Vage and Bogomolov, Emil and Panozzo, Daniele and Zorin, Denis and Burnaev, Evgeny},
doi = {10.1145/3528223.3530140},
issn = {0730-0301},
issue_date = {July 2022},
journal = {ACM Trans. Graph.},
keywords = {curve extraction, sharp geometric features, deep learning},
month = {jul},
number = {4},
numpages = {22},
publisher = {Association for Computing Machinery},
title = {DEF: Deep Estimation of Sharp Geometric Features in 3D Shapes},
url = {https://doi.org/10.1145/3528223.3530140},
volume = {41},
year = {2022}
}
