BD-TNet: Balanced Density-Aware Point Cloud Completion Method Assisted by Trie-Like Shape Prior Embedding Dictionary
IEEE Transactions on Circuits and Systems for Video Technology · 2026-07 · 36 (7) · 9901-9915
DOI: 10.1109/tcsvt.2026.3671782 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Circuits and Systems for Video Technology, 2026-07. Verfasst von Ran Jia und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 83 Literaturangaben. Gefördert von: Sichuan Science and Technology Program, Special Environment Digital Manufacturing Equipment Technology Innovation Center.
Abstract (Originalsprache)
Point cloud completion is a fundamental yet challenging task in 3D computer vision. While existing two-stage methods have made significant progress in shape completion, they often overlook the critical issue of point density imbalance, leading to geometrically unsound results with illusory completeness. In this paper, we propose BD-TNet, a novel balanced density-aware point cloud completion method that systematically addresses this overlooked problem. Specifically, we design a Partial-Connected U-Net structure that strategically reduces top-layer skip connections to rebalance the influence between explicit features of partial inputs and abstract features for predicting missing regions, thereby generating uniformly distributed seed points. Furthermore, we introduce EmbeddingTrie, a Trie-like hierarchical shape prior dictionary that enables adaptive multi-scale prior fusion through a divide-and-conquer strategy. To directly constrain local point density, we devise an Elastic Potential Energy Loss that models point clouds as spring systems, effectively guiding the optimization toward balanced distributions. We evaluate our method on PCN, ShapeNet-34/55, and KITTI datasets, and the results demonstrate that BD-TNet achieves state-of-the-art performance on Density-aware Chamfer Distance while producing visually superior, complete point clouds with balanced density distribution.
Förderung
- Sichuan Science and Technology Program
- Special Environment Digital Manufacturing Equipment Technology Innovation Center
Zitieren
APA
Jia, R., Xue, J., Ma, S., Guo, Z., Wang, K., & Lu, W. (2026). BD-TNet: Balanced Density-Aware Point Cloud Completion Method Assisted by Trie-Like Shape Prior Embedding Dictionary. IEEE Transactions on Circuits and Systems for Video Technology, 36(7), 9901-9915. https://doi.org/10.1109/tcsvt.2026.3671782
Vancouver
Jia R, Xue J, Ma S, Guo Z, Wang K, Lu W. BD-TNet: Balanced Density-Aware Point Cloud Completion Method Assisted by Trie-Like Shape Prior Embedding Dictionary. IEEE Transactions on Circuits and Systems for Video Technology. 2026;36(7):9901-9915. doi:10.1109/tcsvt.2026.3671782
BibTeX
@article{Jia2026,
author = {Jia, Ran and Xue, Junpeng and Ma, Shuai and Guo, Zi and Wang, Kelei and Lu, Wenbo},
title = {BD-TNet: Balanced Density-Aware Point Cloud Completion Method Assisted by Trie-Like Shape Prior Embedding Dictionary},
journal = {IEEE Transactions on Circuits and Systems for Video Technology},
year = {2026},
volume = {36},
number = {7},
pages = {9901--9915},
doi = {10.1109/tcsvt.2026.3671782}
}
EUVIMED