通过全局与局部特征并行学习，提升点云上采样精度与鲁棒性。
Representation Learning of Point Cloud Upsampling in Global and Local Inputs
- 双输入设计：分别处理全局均匀分段与局部补丁特征
- 在多个数据集上实现几何保真度与噪声鲁棒性提升
- 适合需要高精度3D重建的工业与医疗场景
近年来，点云上采样广泛应用于3D重建和物体识别等任务。本文提出一种新框架ReLPU，通过显式学习点云的全局与局部结构特征来提升上采样性能。具体而言，从均匀分段输入（Average Segments）中提取全局特征，从同一点云的补丁输入中提取局部特征，二者经并行自编码器处理后融合，并输入共享解码器进行上采样。这种双输入设计增强了特征完整性与跨尺度一致性，尤其在稀疏和噪声区域表现更优。该框架被应用于多个先进的基于自编码器的网络，在标准数据集上验证，实验结果表明几何保真度和鲁棒性均有持续提升。此外，显著性图分析证实，并行的全局-局部学习显著增强了点云上采样的可解释性与性能。
原文摘要 · Abstract (English)
In recent years, point cloud upsampling has been widely applied in tasks such as 3D reconstruction and object recognition. This study proposed a novel framework, ReLPU, which enhances upsampling performance by explicitly learning from both global and local structural features of point clouds. Specifically, we extracted global features from uniformly segmented inputs (Average Segments) and local features from patch-based inputs of the same point cloud. These two types of features were processed through parallel autoencoders, fused, and then fed into a shared decoder for upsampling. This dual-input design improved feature completeness and cross-scale consistency, especially in sparse and noisy regions. Our framework was applied to several state-of-the-art autoencoder-based networks and validated on standard datasets. Experimental results demonstrated consistent improvements in geometric fidelity and robustness. In addition, saliency maps confirmed that parallel global-local learning significantly enhanced the interpretability and performance of point cloud upsampling.
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。