# Cascaded Non-local Neural Network for Point Cloud Semantic Segmentation

arXiv: https://arxiv.org/abs/2007.15488 · HTML: https://mlsanity.com/paper/2007.15488/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2020.

## Built on by (most cited first, 12 of 12)

- [Instance Segmentation in 3D Scenes using Semantic Superpoint Tree Networks](https://mlsanity.com/paper/2108.07478/) (2021)
- [3D Siamese Voxel-to-BEV Tracker for Sparse Point Clouds](https://mlsanity.com/paper/2111.04426/) (2021)
- [Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2301.10100/) (2023)
- [LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds](https://mlsanity.com/paper/2210.08064/) (2022)
- [Self-Supervised 3D Scene Flow Estimation Guided by Superpoints](https://mlsanity.com/paper/2305.02528/) (2023)
- [Superpoint-guided Semi-supervised Semantic Segmentation of 3D Point Clouds](https://mlsanity.com/paper/2107.03601/) (2021)
- [SSPU-Net: Self-Supervised Point Cloud Upsampling via Differentiable Rendering](https://mlsanity.com/paper/2108.00454/) (2021)
- [Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentation](https://mlsanity.com/paper/2210.05534/) (2022)
- [Language-Level Semantics Conditioned 3D Point Cloud Segmentation](https://mlsanity.com/paper/2107.00430/) (2021)
- [Multi-to-Single Knowledge Distillation for Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2304.14800/) (2023)
- [EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentation](https://mlsanity.com/paper/2512.00385/) (2025)
- [Geometry-Aware 3D Salient Object Detection Network](https://mlsanity.com/paper/2502.16488/) (2025)

## Abstract (arXiv)

In this paper, we propose a cascaded non-local neural network for point cloud segmentation. The proposed network aims to build the long-range dependencies of point clouds for the accurate segmentation. Specifically, we develop a novel cascaded non-local module, which consists of the neighborhood-level, superpoint-level and global-level non-local blocks. First, in the neighborhood-level block, we extract the local features of the centroid points of point clouds by assigning different weights to the neighboring points. The extracted local features of the centroid points are then used to encode the superpoint-level block with the non-local operation. Finally, the global-level block aggregates the non-local features of the superpoints for semantic segmentation in an encoder-decoder framework. Benefiting from the cascaded structure, geometric structure information of different neighborhoods with the same label can be propagated. In addition, the cascaded structure can largely reduce the computational cost of the original non-local operation on point clouds. Experiments on different indoor and outdoor datasets show that our method achieves state-of-the-art performance and effectively reduces the time consumption and memory occupation.