Polarization Wavefront Lidar: Learning Large Scene Reconstruction from Polarized Wavefronts

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Scheuble, Dominik, Lei, Chenyang, Baek, Seung-Hwan, Bijelic, Mario, Heide, Felix
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910481748328448
author Scheuble, Dominik
Lei, Chenyang
Baek, Seung-Hwan
Bijelic, Mario
Heide, Felix
author_facet Scheuble, Dominik
Lei, Chenyang
Baek, Seung-Hwan
Bijelic, Mario
Heide, Felix
contents Lidar has become a cornerstone sensing modality for 3D vision, especially for large outdoor scenarios and autonomous driving. Conventional lidar sensors are capable of providing centimeter-accurate distance information by emitting laser pulses into a scene and measuring the time-of-flight (ToF) of the reflection. However, the polarization of the received light that depends on the surface orientation and material properties is usually not considered. As such, the polarization modality has the potential to improve scene reconstruction beyond distance measurements. In this work, we introduce a novel long-range polarization wavefront lidar sensor (PolLidar) that modulates the polarization of the emitted and received light. Departing from conventional lidar sensors, PolLidar allows access to the raw time-resolved polarimetric wavefronts. We leverage polarimetric wavefronts to estimate normals, distance, and material properties in outdoor scenarios with a novel learned reconstruction method. To train and evaluate the method, we introduce a simulated and real-world long-range dataset with paired raw lidar data, ground truth distance, and normal maps. We find that the proposed method improves normal and distance reconstruction by 53\% mean angular error and 41\% mean absolute error compared to existing shape-from-polarization (SfP) and ToF methods. Code and data are open-sourced at https://light.princeton.edu/pollidar.
format Preprint
id arxiv_https___arxiv_org_abs_2406_03461
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Polarization Wavefront Lidar: Learning Large Scene Reconstruction from Polarized Wavefronts
Scheuble, Dominik
Lei, Chenyang
Baek, Seung-Hwan
Bijelic, Mario
Heide, Felix
Computer Vision and Pattern Recognition
Image and Video Processing
Lidar has become a cornerstone sensing modality for 3D vision, especially for large outdoor scenarios and autonomous driving. Conventional lidar sensors are capable of providing centimeter-accurate distance information by emitting laser pulses into a scene and measuring the time-of-flight (ToF) of the reflection. However, the polarization of the received light that depends on the surface orientation and material properties is usually not considered. As such, the polarization modality has the potential to improve scene reconstruction beyond distance measurements. In this work, we introduce a novel long-range polarization wavefront lidar sensor (PolLidar) that modulates the polarization of the emitted and received light. Departing from conventional lidar sensors, PolLidar allows access to the raw time-resolved polarimetric wavefronts. We leverage polarimetric wavefronts to estimate normals, distance, and material properties in outdoor scenarios with a novel learned reconstruction method. To train and evaluate the method, we introduce a simulated and real-world long-range dataset with paired raw lidar data, ground truth distance, and normal maps. We find that the proposed method improves normal and distance reconstruction by 53\% mean angular error and 41\% mean absolute error compared to existing shape-from-polarization (SfP) and ToF methods. Code and data are open-sourced at https://light.princeton.edu/pollidar.
title Polarization Wavefront Lidar: Learning Large Scene Reconstruction from Polarized Wavefronts
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2406.03461