计算机科学
人工智能
分割
杠杆(统计)
计算机视觉
特征(语言学)
钥匙(锁)
集合(抽象数据类型)
特征提取
稳健性(进化)
点(几何)
融合
任务(项目管理)
光学(聚焦)
可视化
模式识别(心理学)
点云
卷积神经网络
语义学(计算机科学)
语义鸿沟
窗口(计算)
图像分割
骨料(复合)
限制
图像融合
滑动窗口协议
作者
Nan Ma,Zhijie Liu,Yiheng Han
标识
DOI:10.1609/aaai.v40i10.37723
摘要
LiDAR semantic segmentation is a key task in advanced autonomous driving systems. Projection-based methods exhibit real-time potential due to their efficiency, but suffer from inevitable 3D information loss and rely on time-consuming post-processing, limiting overall performance. To address this, we propose MFINet, a real-time semantic segmentation network based on multi-view fusion and 2D-3D interaction enhancement. It adopts a three-branch architecture that integrates 3D Point View (3D-PV), 2D Bird’s Eye View (2D-BEV) and 2D Range View (2D-RV) to make full use of 2D and 3D representation. From 3D to 2D, we design a 3D Point Feature Projector (3DPFP), which injects 3D features into the 2D BEV and RV pseudo-images to retain effective 3D information. From 2D to 3D, a Feature Enhancement (FE) module is designed to leverage the advantages of 2D information in extracting geometric and semantic features. We also introduce a 2D-3D Fusion Head (FH) to aggregate point features from multiple views. Besides, we incorporate a Multi-Scale Dilated Attention (MSDA) module with a sliding window strategy to enhance feature discrimination. Extensive experiments on the SemanticKITTI and NuScenes benchmarks demonstrate that MFINet outperforms existing methods on the SemanticKITTI, NuScenes val set and achieves competitive results on the NuScenes test set.
科研通智能强力驱动
Strongly Powered by AbleSci AI