论文标题
窗口归一化：通过统一不一致的点密度来增强点云理解
Window Normalization: Enhancing Point Cloud Understanding by Unifying Inconsistent Point Densities
论文作者
论文摘要
降采样和特征提取是3D点云理解的重要过程。现有方法受到点云中不同部分的点密度不一致的限制。在这项工作中，我们分析了下采样阶段的局限性，并提出了预先放弃的群体窗口正态分子化模块。特别是，利用窗口范围的方法来统一不同部分的点密度。此外，提出了群体策略以获得多类型特征，包括纹理和空间信息。我们还提出了预言模块，以平衡本地和全局功能。广泛的实验表明，我们的模块在多个任务上的表现更好。在S3DIS（区域5）上的分割任务中，所提出的模块在小对象识别上的性能更好，并且结果比其他模块具有更精确的边界。沙发和色谱柱的识别从69.2％提高到84.4％，分别从42.7％提高到48.7％。基准从71.7％/77.6％/91.9％（MIOU/MACC/OA）提高到72.2％/78.2％/91.4％。 S3DIS上6倍交叉验证的精度为77.6％/85.8％/91.7％。它的表现优于最佳型号PointNext-XL（74.9％/83.0％/90.3％），而MIOU和实现最先进的性能。代码和模型可在https://github.com/dbdxss/window-normalization.git上获得。
Downsampling and feature extraction are essential procedures for 3D point cloud understanding. Existing methods are limited by the inconsistent point densities of different parts in the point cloud. In this work, we analyze the limitation of the downsampling stage and propose the pre-abstraction group-wise window-normalization module. In particular, the window-normalization method is leveraged to unify the point densities in different parts. Furthermore, the group-wise strategy is proposed to obtain multi-type features, including texture and spatial information. We also propose the pre-abstraction module to balance local and global features. Extensive experiments show that our module performs better on several tasks. In segmentation tasks on S3DIS (Area 5), the proposed module performs better on small object recognition, and the results have more precise boundaries than others. The recognition of the sofa and the column is improved from 69.2% to 84.4% and from 42.7% to 48.7%, respectively. The benchmarks are improved from 71.7%/77.6%/91.9% (mIoU/mAcc/OA) to 72.2%/78.2%/91.4%. The accuracies of 6-fold cross-validation on S3DIS are 77.6%/85.8%/91.7%. It outperforms the best model PointNeXt-XL (74.9%/83.0%/90.3%) by 2.7% on mIoU and achieves state-of-the-art performance. The code and models are available at https://github.com/DBDXSS/Window-Normalization.git.
