Deep Interactive Volume Exploration Through Pre-Trained 3D CNN and Active Learning

Marwa Salhi, Riadh Ksantini, Belhassen Zouari

2023

Abstract

Direct volume rendering (DVR) is a powerful technique for visualizing 3D images. Though, generating high-quality efficient rendering results is still a challenging task because of the complexity of volumetric datasets. This paper introduces a direct volume rendering framework based on 3D CNN and active learning. First, a pre-trained 3D CNN was developed to extract deep features while minimizing the loss of information. Then, the 3D CNN was incorporated into the proposed image-centric system to generate a transfer function for DVR. The method employs active learning by involving incremental classification along with user interaction. The interactive process is simple, and the rendering result is generated in real-time. We conducted extensive experiments on many volumetric datasets achieving qualitative and quantitative results outperforming state-of-the-art approaches.

Paper Citation

in Harvard Style

Salhi M., Ksantini R. and Zouari B. (2023). Deep Interactive Volume Exploration Through Pre-Trained 3D CNN and Active Learning. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 1: GRAPP; ISBN 978-989-758-634-7, SciTePress, pages 170-178. DOI: 10.5220/0011638500003417

in Bibtex Style

@conference{grapp23,
author={Marwa Salhi and Riadh Ksantini and Belhassen Zouari},
title={Deep Interactive Volume Exploration Through Pre-Trained 3D CNN and Active Learning},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 1: GRAPP},
year={2023},
pages={170-178},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011638500003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 1: GRAPP
TI - Deep Interactive Volume Exploration Through Pre-Trained 3D CNN and Active Learning
SN - 978-989-758-634-7
AU - Salhi M.
AU - Ksantini R.
AU - Zouari B.
PY - 2023
SP - 170
EP - 178
DO - 10.5220/0011638500003417
PB - SciTePress