CloudMix : Dual Mixup Consistency for Unpaired Point Cloud Completion

Due to the unsatisfactory performance of supervised methods on unpaired real-world scans, point cloud completion via cross-domain adaptation has recently drawn growing attention. Nevertheless, previous approaches only focus on alleviating the distribution shift through domain alignment, resulting in...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on visualization and computer graphics. - 1996. - PP(2024) vom: 01. Apr.
1. Verfasser: Liu, Fengqi (VerfasserIn)
Weitere Verfasser: Gong, Jingyu, Zhou, Qianyu, Lu, Xuequan, Yi, Ran, Xie, Yuan, Ma, Lizhuang
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2024
Zugriff auf das übergeordnete Werk:IEEE transactions on visualization and computer graphics
Schlagworte:Journal Article
Beschreibung
Zusammenfassung:Due to the unsatisfactory performance of supervised methods on unpaired real-world scans, point cloud completion via cross-domain adaptation has recently drawn growing attention. Nevertheless, previous approaches only focus on alleviating the distribution shift through domain alignment, resulting in massive information loss of real-world domain data. To tackle this issue, we propose a dual mixup-induced consistency regularization to integrate both source and target domain to improve robustness and generalization capability. Specifically, we mix up virtual and real-world shapes in the input and latent feature space respectively, and then regularize the completion network by forcing two kinds of mixed completion predictions to be consistent. To further adapt to each instance within the real-world domain, we design a novel density-aware refiner to utilize local context information to preserve the fine-grained details and remove noise or outliers for coarse completion. Extensive experiments on real-world scans and our synthetic unpaired datasets demonstrate the superiority of our method over existing state-of-the-art approaches
Beschreibung:Date Revised 01.04.2024
published: Print-Electronic
Citation Status Publisher
ISSN:1941-0506
DOI:10.1109/TVCG.2024.3383434