TY - GEN
T1 - SGPCR
T2 - 23rd IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2023
AU - Salihu, Driton
AU - Steinbach, Eckehard
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Retrieving and aligning CAD models from databases with scanned real-world point clouds remains an important topic for 3D reconstruction. Due to zero point-to-point correspondences between the sampled CAD model and the scanned real-world object, an information-rich representation of point clouds is needed. We propose SGPCR, a novel method for representing 3D point clouds by Spherical Gaussians for efficient, stable, and rotation-equivariant representation. We also propose a rotation-invariant convolution to improve the representation quality through a trainable optimization process. In addition, we demonstrate the strengths of SGPCR-based point cloud representation using the fundamental challenge of shape retrieval and point cloud registration on point clouds with zero point-to-point correspondences. Under these conditions, our approach improves registration quality by reducing chamfer distance by up to 90% and rotation root mean square error by up to 86% compared to the state of the art. Furthermore, the proposed SGCPR is used for one-shot shape retrieval and registration and improves retrieval precision by up to 58% over comparable methods.
AB - Retrieving and aligning CAD models from databases with scanned real-world point clouds remains an important topic for 3D reconstruction. Due to zero point-to-point correspondences between the sampled CAD model and the scanned real-world object, an information-rich representation of point clouds is needed. We propose SGPCR, a novel method for representing 3D point clouds by Spherical Gaussians for efficient, stable, and rotation-equivariant representation. We also propose a rotation-invariant convolution to improve the representation quality through a trainable optimization process. In addition, we demonstrate the strengths of SGPCR-based point cloud representation using the fundamental challenge of shape retrieval and point cloud registration on point clouds with zero point-to-point correspondences. Under these conditions, our approach improves registration quality by reducing chamfer distance by up to 90% and rotation root mean square error by up to 86% compared to the state of the art. Furthermore, the proposed SGCPR is used for one-shot shape retrieval and registration and improves retrieval precision by up to 58% over comparable methods.
KW - Algorithms: 3D computer vision
KW - Machine learning architectures
KW - and algorithms (including transfer, low-shot, semi-, self-, and un-supervised learning)
KW - formulations
UR - http://www.scopus.com/inward/record.url?scp=85147550810&partnerID=8YFLogxK
U2 - 10.1109/WACV56688.2023.00064
DO - 10.1109/WACV56688.2023.00064
M3 - Conference contribution
AN - SCOPUS:85147550810
T3 - Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
SP - 572
EP - 581
BT - Proceedings - 2023 IEEE Winter Conference on Applications of Computer Vision, WACV 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 3 January 2023 through 7 January 2023
ER -