TY - GEN
T1 - MatchMakerNet
T2 - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
AU - Villegas-Suarez, Ariana M.
AU - Lopez, Cristian
AU - Sipiran, Ivan
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Automating the reassembly of fragmented objects is a complex task with applications in cultural heritage preservation, paleontology, and medicine. However, the matching subtask of the reassembly process has received limited attention, despite its crucial role in reducing the alignment search space. To address this gap, we propose Match-MakerNet, a network architecture designed to automate the pairing of object fragments for reassembly. By taking two point clouds as input and leveraging graph convolution alongside a simplified version of DGCNN, MatchMakerNet achieves remarkable results. After training on the Artifact (synthetic) dataset, we achieve an accuracy of 87.31% in all-to-all comparisons between the fragments. In addition, it demonstrates robust generalization capabilities, achieving 86.93% accuracy on the Everyday (synthetic) dataset and 83.03% on the Puzzles 3D (real-world) dataset. These findings highlight the effectiveness and versatility of Match-MakerNet in solving the matching subtask.
AB - Automating the reassembly of fragmented objects is a complex task with applications in cultural heritage preservation, paleontology, and medicine. However, the matching subtask of the reassembly process has received limited attention, despite its crucial role in reducing the alignment search space. To address this gap, we propose Match-MakerNet, a network architecture designed to automate the pairing of object fragments for reassembly. By taking two point clouds as input and leveraging graph convolution alongside a simplified version of DGCNN, MatchMakerNet achieves remarkable results. After training on the Artifact (synthetic) dataset, we achieve an accuracy of 87.31% in all-to-all comparisons between the fragments. In addition, it demonstrates robust generalization capabilities, achieving 86.93% accuracy on the Everyday (synthetic) dataset and 83.03% on the Puzzles 3D (real-world) dataset. These findings highlight the effectiveness and versatility of Match-MakerNet in solving the matching subtask.
KW - computer vision
KW - objects 3d
KW - reassembly
UR - http://www.scopus.com/inward/record.url?scp=85182936936&partnerID=8YFLogxK
U2 - 10.1109/ICCVW60793.2023.00178
DO - 10.1109/ICCVW60793.2023.00178
M3 - Conference contribution
AN - SCOPUS:85182936936
T3 - Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
SP - 1624
EP - 1633
BT - Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 2 October 2023 through 6 October 2023
ER -