DMF-Net: Image-Guided Point Cloud Completion with Dual-Channel Modality Fusion and Shape-Aware Upsampling Transformer
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (6) · 6063-6071
DOI: 10.1609/aaai.v39i6.32648 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Aihua Mao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref).
Abstract (Originalsprache)
In this paper we study the task of a single-view image-guided point cloud completion. Existing methods have got promising results by fusing the information of image into point cloud explicitly or implicitly. However, given that the image has global shape information and the partial point cloud has rich local details, We believe that both modalities need to be given equal attention when performing modality fusion. To this end, we propose a novel dual-channel modality fusion network for image-guided point cloud completion(named DMF-Net), in a coarse-to-fine manner. In the first stage, DMF-Net takes a partial point cloud and corresponding image as input to recover a coarse point cloud. In the second stage, the coarse point cloud will be upsampled twice with shape-aware upsampling transformer to get the dense and complete point cloud. Extensive quantitative and qualitative experimental results show that DMF-Net outperforms the state-of-the-art unimodal and multimodal point cloud completion works on ShapeNet-ViPC dataset.
Zitieren
APA
Mao, A., Tang, Y., Huang, J., & He, Y. (2025). DMF-Net: Image-Guided Point Cloud Completion with Dual-Channel Modality Fusion and Shape-Aware Upsampling Transformer. Proceedings of the AAAI Conference on Artificial Intelligence, 39(6), 6063-6071. https://doi.org/10.1609/aaai.v39i6.32648
Vancouver
Mao A, Tang Y, Huang J, He Y. DMF-Net: Image-Guided Point Cloud Completion with Dual-Channel Modality Fusion and Shape-Aware Upsampling Transformer. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(6):6063-6071. doi:10.1609/aaai.v39i6.32648
BibTeX
@article{Mao2025,
author = {Mao, Aihua and Tang, Yuxuan and Huang, Jiangtao and He, Ying},
title = {DMF-Net: Image-Guided Point Cloud Completion with Dual-Channel Modality Fusion and Shape-Aware Upsampling Transformer},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {6},
pages = {6063--6071},
doi = {10.1609/aaai.v39i6.32648}
}
EUVIMED