PointSea: Point Cloud Completion via Self-structure Augmentation
International Journal of Computer Vision · 2025-07 · 133 (7) · 4770-4794
DOI: 10.1007/s11263-025-02400-y ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer Vision, online erschienen am 19.03.2025. Verfasst von Zhe Zhu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 109 Literaturangaben.
Abstract (Originalsprache)
Point cloud completion is a fundamental yet not well-solved problem in 3D vision. Current approaches often rely on 3D coordinate information and/or additional data (e.g., images and scanning viewpoints) to fill in missing parts. Unlike these methods, we explore self-structure augmentation and propose PointSea for global-to-local point cloud completion. In the global stage, consider how we inspect a defective region of a physical object, we may observe it from various perspectives for a better understanding. Inspired by this, PointSea augments data representation by leveraging self-projected depth images from multiple views. To reconstruct a compact global shape from the cross-modal input, we incorporate a feature fusion module to fuse features at both intra-view and inter-view levels. In the local stage, to reveal highly detailed structures, we introduce a point generator called the self-structure dual-generator. This generator integrates both learned shape priors and geometric self-similarities for shape refinement. Unlike existing efforts that apply a unified strategy for all points, our dual-path design adapts refinement strategies conditioned on the structural type of each point, addressing the specific incompleteness of each point. Comprehensive experiments on widely-used benchmarks demonstrate that PointSea effectively understands global shapes and generates local details from incomplete input, showing clear improvements over existing methods. Our code is available at https://github.com/czvvd/SVDFormer_PointSea.
Zitieren
APA
Zhu, Z., Chen, H., He, X., & Wei, M. (2025). PointSea: Point Cloud Completion via Self-structure Augmentation. International Journal of Computer Vision, 133(7), 4770-4794. https://doi.org/10.1007/s11263-025-02400-y
Vancouver
Zhu Z, Chen H, He X, Wei M. PointSea: Point Cloud Completion via Self-structure Augmentation. International Journal of Computer Vision. 2025;133(7):4770-4794. doi:10.1007/s11263-025-02400-y
BibTeX
@article{Zhu2025,
author = {Zhu, Zhe and Chen, Honghua and He, Xing and Wei, Mingqiang},
title = {PointSea: Point Cloud Completion via Self-structure Augmentation},
journal = {International Journal of Computer Vision},
year = {2025},
volume = {133},
number = {7},
pages = {4770--4794},
doi = {10.1007/s11263-025-02400-y}
}
EUVIMED