Guardado en:
Detalles Bibliográficos
Autores principales: Li, Aocheng, Zimmer-Dauphinee, James R., Kalyanam, Rajesh, Lindsay, Ian, VanValkenburgh, Parker, Wernke, Steven, Aliaga, Daniel
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2503.04030
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916645085118464
author Li, Aocheng
Zimmer-Dauphinee, James R.
Kalyanam, Rajesh
Lindsay, Ian
VanValkenburgh, Parker
Wernke, Steven
Aliaga, Daniel
author_facet Li, Aocheng
Zimmer-Dauphinee, James R.
Kalyanam, Rajesh
Lindsay, Ian
VanValkenburgh, Parker
Wernke, Steven
Aliaga, Daniel
contents Point cloud completion helps restore partial incomplete point clouds suffering occlusions. Current self-supervised methods fail to give high fidelity completion for large objects with missing surfaces and unbalanced distribution of available points. In this paper, we present a novel method for restoring large-scale point clouds with limited and imbalanced ground-truth. Using rough boundary annotations for a region of interest, we project the original point clouds into a multiple-center-of-projection (MCOP) image, where fragments are projected to images of 5 channels (RGB, depth, and rotation). Completion of the original point cloud is reduced to inpainting the missing pixels in the MCOP images. Due to lack of complete structures and an unbalanced distribution of existing parts, we develop a self-supervised scheme which learns to infill the MCOP image with points resembling existing "complete" patches. Special losses are applied to further enhance the regularity and consistency of completed MCOP images, which is mapped back to 3D to form final restoration. Extensive experiments demonstrate the superiority of our method in completing 600+ incomplete and unbalanced archaeological structures in Peru.
format Preprint
id arxiv_https___arxiv_org_abs_2503_04030
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Self-Supervised Large Scale Point Cloud Completion for Archaeological Site Restoration
Li, Aocheng
Zimmer-Dauphinee, James R.
Kalyanam, Rajesh
Lindsay, Ian
VanValkenburgh, Parker
Wernke, Steven
Aliaga, Daniel
Computer Vision and Pattern Recognition
Point cloud completion helps restore partial incomplete point clouds suffering occlusions. Current self-supervised methods fail to give high fidelity completion for large objects with missing surfaces and unbalanced distribution of available points. In this paper, we present a novel method for restoring large-scale point clouds with limited and imbalanced ground-truth. Using rough boundary annotations for a region of interest, we project the original point clouds into a multiple-center-of-projection (MCOP) image, where fragments are projected to images of 5 channels (RGB, depth, and rotation). Completion of the original point cloud is reduced to inpainting the missing pixels in the MCOP images. Due to lack of complete structures and an unbalanced distribution of existing parts, we develop a self-supervised scheme which learns to infill the MCOP image with points resembling existing "complete" patches. Special losses are applied to further enhance the regularity and consistency of completed MCOP images, which is mapped back to 3D to form final restoration. Extensive experiments demonstrate the superiority of our method in completing 600+ incomplete and unbalanced archaeological structures in Peru.
title Self-Supervised Large Scale Point Cloud Completion for Archaeological Site Restoration
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.04030