DANCE: Density-agnostic and Class-aware Network for Point Cloud Completion
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (7) · 5648-5655
DOI: 10.1609/aaai.v40i7.37484 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Da-Yeong Kim und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Point cloud completion aims to recover missing geometric structures from incomplete 3D scans, which often suffer from occlusions or limited sensor viewpoints. Existing methods typically assume fixed input/output densities or rely on image-based representations, making them less suitable for real-world scenarios with variable sparsity and limited supervision. In this paper, we introduce Density-agnostic and Class-aware Network (DANCE), a novel framework that completes only the missing regions while preserving the observed geometry. DANCE generates candidate points via ray-based sampling from multiple viewpoints. A transformer decoder then refines their positions and predicts opacity scores, which determine the validity of each point for inclusion in the final surface. To incorporate semantic guidance, a lightweight classification head is trained directly on geometric features, enabling category-consistent completion without external image supervision. Extensive experiments on the PCN and MVP benchmarks show that DANCE outperforms state-of-the-art methods in accuracy and structural consistency, while remaining robust to varying input densities and noise levels.
Zitieren
APA
Kim, D., & Cho, Y. (2026). DANCE: Density-agnostic and Class-aware Network for Point Cloud Completion. Proceedings of the AAAI Conference on Artificial Intelligence, 40(7), 5648-5655. https://doi.org/10.1609/aaai.v40i7.37484
Vancouver
Kim D, Cho Y. DANCE: Density-agnostic and Class-aware Network for Point Cloud Completion. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(7):5648-5655. doi:10.1609/aaai.v40i7.37484
BibTeX
@article{Kim2026,
author = {Kim, Da-Yeong and Cho, Yeong-Jun},
title = {DANCE: Density-agnostic and Class-aware Network for Point Cloud Completion},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {7},
pages = {5648--5655},
doi = {10.1609/aaai.v40i7.37484}
}
EUVIMED