MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understanding

by   Kunyu Peng, et al.

At the heart of all automated driving systems is the ability to sense the surroundings, e.g., through semantic segmentation of LiDAR sequences, which experienced a remarkable progress due to the release of large datasets such as SemanticKITTI and nuScenes-LidarSeg. While most previous works focus on sparse segmentation of the LiDAR input, dense output masks provide self-driving cars with almost complete environment information. In this paper, we introduce MASS - a Multi-Attentional Semantic Segmentation model specifically built for dense top-view understanding of the driving scenes. Our framework operates on pillar- and occupancy features and comprises three attention-based building blocks: (1) a keypoint-driven graph attention, (2) an LSTM-based attention computed from a vector embedding of the spatial input, and (3) a pillar-based attention, resulting in a dense 360-degree segmentation mask. With extensive experiments on both, SemanticKITTI and nuScenes-LidarSeg, we quantitatively demonstrate the effectiveness of our model, outperforming the state of the art by 19.0 SemanticKITTI and reaching 32.7 the first work addressing the dense segmentation task. Furthermore, our multi-attention model is shown to be very effective for 3D object detection validated on the KITTI-3D dataset, showcasing its high generalizability to other tasks related to 3D vision.


page 1

page 10

page 11

page 12


A Dataset for Semantic Segmentation of Point Cloud Sequences

Semantic scene understanding is important for various applications. In p...

PointPainting: Sequential Fusion for 3D Object Detection

Camera and lidar are important sensor modalities for robotics in general...

LidarMultiNet: Unifying LiDAR Semantic Segmentation, 3D Object Detection, and Panoptic Segmentation in a Single Multi-task Network

This technical report presents the 1st place winning solution for the Wa...

A Benchmark for LiDAR-based Panoptic Segmentation based on KITTI

Panoptic segmentation is the recently introduced task that tackles seman...

SphNet: A Spherical Network for Semantic Pointcloud Segmentation

Semantic segmentation for robotic systems can enable a wide range of app...

MaskRange: A Mask-classification Model for Range-view based LiDAR Segmentation

Range-view based LiDAR segmentation methods are attractive for practical...

Pit30M: A Benchmark for Global Localization in the Age of Self-Driving Cars

We are interested in understanding whether retrieval-based localization ...

Please sign up or login with your details

Forgot password? Click here to reset