Multilateral Cascading Network for Semantic Segmentation of Large-Scale Outdoor Point Clouds

2024-09-21 · Haoran Gong, Haodong Wang, Di Wang

Semantic segmentation of large-scale outdoor point clouds is of significant importance in environment perception and scene understanding. However, this task continues to present a significant research challenge, due to the inherent complexity of outdoor objects and their diverse distributions in real-world environments. In this study, we propose the Multilateral Cascading Network (MCNet) designed to address this challenge. The model comprises two key components: a Multilateral Cascading Attention Enhancement (MCAE) module, which facilitates the learning of complex local features through multilateral cascading operations; and a Point Cross Stage Partial (P-CSP) module, which fuses global and local features, thereby optimizing the integration of valuable feature information across multiple scales. Our proposed method demonstrates superior performance relative to state-of-the-art approaches across two widely recognized benchmark datasets: Toronto3D and SensatUrban. Especially on the city-scale SensatUrban dataset, our results surpassed the current best result by 2.1\% in overall mIoU and yielded an improvement of 15.9\% on average for small-sample object categories comprising less than 2\% of the total samples, in comparison to the baseline method.

📄 PDF Abstract BibTeX arXiv:2409.13983

Code (0)

등록된 구현이 없습니다.

Tasks

Scene Understanding Semantic Segmentation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Attention 설명 없음

Neovascularization Segmentation via a Multilateral Interaction-Enhanced Graph Convolutional Network

2025-08-05 · Tao Chen, Dan Zhang, Da Chen, Huazhu Fu 외 arxiv

Choroidal neovascularization (CNV), a primary characteristic of wet age-related macular degeneration (wet AMD), represents a leading cause of blindness worldwide. In clinical practice, optical coherence tomography angiog…

Multilateral matching with scale economies

2023-10-30 · Chao Huang

This paper studies multilateral matching in which agents may negotiate contracts within any coalition. We assume scale economies such that an agent substitutes some existing contracts with new ones only if the latter inv…

Hypergraph-Induced Semantic Tuplet Loss for Deep Metric Learning

2022-01-01 · CVPR 2022 1 · Jongin Lim, Sangdoo Yun, Seulki Park, Jin Young Choi

In this paper, we propose Hypergraph-Induced Semantic Tuplet (HIST) loss for deep metric learning that leverages the multilateral semantic relations of multiple samples to multiple classes via hypergraph modeling. We…

Metric Learning Node Classification

Zero-Splat TeleAssist: A Zero-Shot Pose Estimation Framework for Semantic Teleoperation

2025-12-09 · Srijan Dokania, Dharini Raghavan arxiv

We introduce Zero-Splat TeleAssist, a zero-shot sensor-fusion pipeline that transforms commodity CCTV streams into a shared, 6-DoF world model for multilateral teleoperation. By integrating vision-language segmentation, …

Pose Estimation

MOPaC: The Multiple Offers Protocol for Multilateral Negotiations with Partial Consensus

2022-05-13 · Pradeep K. Murukannaiah, Catholijn M. Jonker

Existing protocols for multilateral negotiation require a full consensus among the negotiating parties. In contrast, we propose a protocol for multilateral negotiation that allows partial consensus, wherein only a subset…