LEST: Large-scale LiDAR Semantic Segmentation with Transformer

2023-07-14 · Chuanyu Luo, Nuo Cheng, Sikun Ma, Han Li, Xiaohan Li, Shengguang Lei, Pu Li

Large-scale LiDAR-based point cloud semantic segmentation is a critical task in autonomous driving perception. Almost all of the previous state-of-the-art LiDAR semantic segmentation methods are variants of sparse 3D convolution. Although the Transformer architecture is becoming popular in the field of natural language processing and 2D computer vision, its application to large-scale point cloud semantic segmentation is still limited. In this paper, we propose a LiDAR sEmantic Segmentation architecture with pure Transformer, LEST. LEST comprises two novel components: a Space Filling Curve (SFC) Grouping strategy and a Distance-based Cosine Linear Transformer, DISCO. On the public nuScenes semantic segmentation validation set and SemanticKITTI test set, our model outperforms all the other state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2307.09367

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous Driving LIDAR Semantic Segmentation Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Position-Wise Feed-Forward Layer 설명 없음

Residual Connection 설명 없음

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Adam 설명 없음

Efficient LiDAR Point Cloud Oversegmentation Network

2023-01-01 · ICCV 2023 1 · Le Hui, Linghua Tang, Yuchao Dai, Jin Xie 외

Point cloud oversegmentation is a challenging task since it needs to produce perceptually meaningful partitions (i.e., superpoints) of a point cloud. Most existing oversegmentation methods cannot efficiently generate…

LIDAR Semantic Segmentation Semantic Segmentation

SN-LiDAR: Semantic Neural Fields for Novel Space-time View LiDAR Synthesis

2025-04-11 · Yi Chen, Tianchen Deng, Wentao Zhao, Xiaoning Wang 외

Recent research has begun exploring novel view synthesis (NVS) for LiDAR point clouds, aiming to generate realistic LiDAR scans from unseen viewpoints. However, most existing approaches do not reconstruct semantic labels…

Autonomous Driving Novel View Synthesis Semantic Segmentation

VolMap: A Real-time Model for Semantic Segmentation of a LiDAR surrounding view

2019-06-12 · Hager Radi, Waleed Ali

This paper introduces VolMap, a real-time approach for the semantic segmentation of a 3D LiDAR surrounding view system in autonomous vehicles. We designed an optimized deep convolution neural network that can accurately …

3D Object Detection Autonomous Vehicles CPU object-detection+3

FRACTAL: An Ultra-Large-Scale Aerial Lidar Dataset for 3D Semantic Segmentation of Diverse Landscapes

2024-05-07 · Charles Gaydon, Michel Daab, Floryne Roche

Mapping agencies are increasingly adopting Aerial Lidar Scanning (ALS) as a new tool to map buildings and other above-ground structures. Processing ALS data at scale requires efficient point classification methods that p…

3D Point Cloud Classification 3D Semantic Segmentation Diversity Point Cloud Classification+1

EfficientLPS: Efficient LiDAR Panoptic Segmentation

2021-02-16 · Kshitij Sirohi, Rohit Mohan, Daniel Büscher, Wolfram Burgard 외

Panoptic segmentation of point clouds is a crucial task that enables autonomous vehicles to comprehend their vicinity using their highly accurate and reliable LiDAR sensors. Existing top-down approaches tackle this probl…

Autonomous Vehicles Instance Segmentation Panoptic Segmentation Segmentation+1