DeepAI AI Chat
Log In Sign Up

Complete Label: A Domain Adaptation Approach to Semantic Segmentation of LiDAR Point Clouds

07/16/2020
by   Li Yi, et al.
Google
0

We study an unsupervised domain adaptation problem for the semantic labeling of 3D point clouds, with a particular focus on domain discrepancies induced by different LiDAR sensors. Based on the observation that sparse 3D point clouds are sampled from 3D surfaces, we take a Complete and Label approach to recover the underlying surfaces before passing them to a segmentation network. Specifically, we design a Sparse Voxel Completion Network (SVCN) to complete the 3D surfaces of a sparse point cloud. Unlike semantic labels, to obtain training pairs for SVCN requires no manual labeling. We also introduce local adversarial learning to model the surface prior. The recovered 3D surfaces serve as a canonical domain, from which semantic labels can transfer across different LiDAR sensors. Experiments and ablation studies with our new benchmark for cross-domain semantic labeling of LiDAR data show that the proposed approach provides 8.2-36.6 adaptation methods.

READ FULL TEXT
07/20/2022

CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation

3D LiDAR semantic segmentation is fundamental for autonomous driving. Se...
01/06/2023

Comparisons of five indices for estimating local terrain surface roughness using LiDAR point clouds

Terrain surface roughness is an abstract concept, and its quantitative d...
10/14/2022

Segmentation-guided Domain Adaptation for Efficient Depth Completion

Complete depth information and efficient estimators have become vital in...
07/03/2019

Analyzing the Cross-Sensor Portability of Neural Network Architectures for LiDAR-based Semantic Labeling

State-of-the-art approaches for the semantic labeling of LiDAR point clo...
05/23/2022

Enhanced Prototypical Learning for Unsupervised Domain Adaptation in LiDAR Semantic Segmentation

Despite its importance, unsupervised domain adaptation (UDA) on LiDAR se...
12/23/2020

Semantic Segmentation on Swiss3DCities: A Benchmark Study on Aerial Photogrammetric 3D Pointcloud Dataset

We introduce a new outdoor urban 3D pointcloud dataset, covering a total...
11/28/2017

3D Semantic Segmentation with Submanifold Sparse Convolutional Networks

Convolutional networks are the de-facto standard for analyzing spatio-te...