Published on:
2 May 2024
Primary Category:
Computer Vision and Pattern Recognition
Paper Authors:
Youquan Liu,
Lingdong Kong,
Xiaoyang Wu,
Runnan Chen,
Xin Li,
Liang Pan,
Ziwei Liu,
Yuexin Ma
Combines multi-task, multi-dataset, and multi-modality data
Conducts alignments in data, feature, and label spaces
Achieves state-of-the-art segmentation performance
Uses a single set of parameters across diverse datasets
Demonstrates strong robustness and generalizability
Universal LiDAR segmentation
This paper presents M3Net, a framework for multi-task, multi-dataset, multi-modality LiDAR segmentation using a single set of parameters. It combines large-scale driving datasets with different sensors and conducts alignments in data, feature, and label spaces during training. This allows M3Net to train state-of-the-art segmentation models by taming heterogeneous data. Experiments on 12 datasets show it achieves top performance on SemanticKITTI, nuScenes, and Waymo using one shared parameter set.
Multi-sensor road segmentation
Multimodal fusion for 3D object detection
Camera-based 3D object detection using multi-dataset training and transformer model
Data-efficient 3D scene understanding for autonomous vehicles
Point cloud semantic features for 3D object detection
Semantic LiDAR Odometry for Fast Moving Vehicles
No comments yet, be the first to start the conversation...
Sign up to comment on this paper