用不平衡最优传输解决无配对点云补全问题，提升真实场景鲁棒性。
Unsupervised Point Cloud Completion through Unbalanced Optimal Transport
- 基于神经网络学习不平衡最优传输映射，实现无配对数据补全
- 在单类与多类基准上表现优异，尤其在类别不平衡下更稳定
- 首个将不平衡最优传输用于点云补全的工作，适合真实场景应用
无配对点云补全是实际应用中的关键任务，因完整点云的真实标签数据通常不可得。通过从无配对的不完整与完整点云数据中学习补全映射，该任务避免了对成对数据集的依赖。本文提出一种名为【不平衡最优传输无配对点云补全（UOT-UPC）】的新模型，将无配对补全任务建模为（不平衡）最优传输问题。我们的方法采用神经最优传输模型，利用神经网络学习不平衡最优传输映射。这是首次尝试将不平衡最优传输应用于无配对点云补全，取得了在单类别和多类别基准上的竞争性或更优性能。特别地，本方法在真实场景中常见的类别不平衡问题下表现出更强的鲁棒性。代码已公开于 https://github.com/LEETK99/UOT-UPC。
原文摘要 · Abstract (English)
Unpaired point cloud completion is crucial for real-world applications, where ground-truth data for complete point clouds are often unavailable. By learning a completion map from unpaired incomplete and complete point cloud data, this task avoids the reliance on paired datasets. In this paper, we propose the \textit{Unbalanced Optimal Transport Map for Unpaired Point Cloud Completion (\textbf{UOT-UPC})} model, which formulates the unpaired completion task as the (Unbalanced) Optimal Transport (OT) problem. Our method employs a Neural OT model learning the UOT map using neural networks. Our model is the first attempt to leverage UOT for unpaired point cloud completion, achieving competitive or superior performance on both single-category and multi-category benchmarks. In particular, our approach is especially robust under the class imbalance problem, which is frequently encountered in real-world unpaired point cloud completion scenarios. The code is available at https://github.com/LEETK99/UOT-UPC.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。