We investigate the problem of 3D point clouds semantic segmentation. Recently, a large amount of research work has focused on local feature aggregation. However, the foundational framework of semantic segmentation of 3D point clouds has been neglected, where the majority of current methods default to the U-Net framework. In this study, we present U-Next, a small but mighty framework designed specifically for point cloud semantic segmentation. The key innovation of this framework is to capture multi-scale hierarchical features. Specifically, we construct the U-Next by stacking multiple U-Net L1 sub-networks in a dense arrangement to diminish the semantic gap. Concurrently, it integrates feature maps across various scales to proficiently restore intricate fine-grained details. Additionally, a multi-level deep supervision mechanism is introduced for smoothing gradient propagation and facilitating network optimization. We conduct extensive experiments on benchmarks, including the indoor S3DIS dataset, the LiDAR-based outdoor Toronto3D dataset, and the urban-scale photogrammetry-based SensatUrban dataset, demonstrate the superiority of U-Next. The U-Next framework consistently exhibits significant performance enhancements across various benchmarks and baselines, demonstrating its considerable potential as a versatile point-based framework for future endeavors. The code has been released at https://github.com/zeng-ziyin/U-Next.

中文翻译：

---

小而强大：使用 U-Next 框架增强 3D 点云语义分割


我们研究了 3D 点云语义分割的问题。最近，大量的研究工作集中在局部特征聚合上。然而，3D 点云语义分割的基础框架被忽视了，目前大多数方法都默认使用 U-Net 框架。在这项研究中，我们提出了 U-Next，这是一个专为点云语义分割而设计的小而强大的框架。该框架的关键创新是捕获多尺度分层特征。具体来说，我们通过将多个 U-Net L1 子网络密集堆叠来构建 U-Next，以减少语义差距。同时，它集成了各种比例的特征图，以熟练地恢复复杂的细粒度细节。此外，还引入了多级深度监督机制，用于平滑梯度传播并促进网络优化。我们对基准进行了广泛的实验，包括室内 S3DIS 数据集、基于 LiDAR 的室外 Toronto3D 数据集和基于城市尺度摄影测量的 SensatUrban 数据集，证明了 U-Next 的优越性。U-Next 框架在各种基准和基线中始终表现出显著的性能增强，展示了其作为未来努力的多功能基于点的框架的巨大潜力。该代码已于 https://github.com/zeng-ziyin/U-Next 发布。