Saved in:
Bibliographic Details
Main Authors: Lin, Ancheng, Li, Jun, Xiang, Yusheng, Bian, Wei, Prasad, Mukesh
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2211.10580
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917919350325248
author Lin, Ancheng
Li, Jun
Xiang, Yusheng
Bian, Wei
Prasad, Mukesh
author_facet Lin, Ancheng
Li, Jun
Xiang, Yusheng
Bian, Wei
Prasad, Mukesh
contents High-quality surface normal can help improve geometry estimation in problems faced by autonomous vehicles, such as collision avoidance and occlusion inference. While a considerable volume of literature focuses on densely scanned indoor scenarios, normal estimation during autonomous driving remains an intricate problem due to the sparse, non-uniform, and noisy nature of real-world LiDAR scans. In this paper, we introduce a multi-modal technique that leverages 3D point clouds and 2D colour images obtained from LiDAR and camera sensors for surface normal estimation. We present the Hybrid Geometric Transformer (HGT), a novel transformer-based neural network architecture that proficiently fuses visual semantic and 3D geometric information. Furthermore, we developed an effective learning strategy for the multi-modal data. Experimental results demonstrate the superior effectiveness of our information fusion approach compared to existing methods. It has also been verified that the proposed model can learn from a simulated 3D environment that mimics a traffic scene. The learned geometric knowledge is transferable and can be applied to real-world 3D scenes in the KITTI dataset. Further tasks built upon the estimated normal vectors in the KITTI dataset show that the proposed estimator has an advantage over existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2211_10580
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Normal Transformer: Extracting Surface Geometry from LiDAR Points Enhanced by Visual Semantics
Lin, Ancheng
Li, Jun
Xiang, Yusheng
Bian, Wei
Prasad, Mukesh
Computer Vision and Pattern Recognition
High-quality surface normal can help improve geometry estimation in problems faced by autonomous vehicles, such as collision avoidance and occlusion inference. While a considerable volume of literature focuses on densely scanned indoor scenarios, normal estimation during autonomous driving remains an intricate problem due to the sparse, non-uniform, and noisy nature of real-world LiDAR scans. In this paper, we introduce a multi-modal technique that leverages 3D point clouds and 2D colour images obtained from LiDAR and camera sensors for surface normal estimation. We present the Hybrid Geometric Transformer (HGT), a novel transformer-based neural network architecture that proficiently fuses visual semantic and 3D geometric information. Furthermore, we developed an effective learning strategy for the multi-modal data. Experimental results demonstrate the superior effectiveness of our information fusion approach compared to existing methods. It has also been verified that the proposed model can learn from a simulated 3D environment that mimics a traffic scene. The learned geometric knowledge is transferable and can be applied to real-world 3D scenes in the KITTI dataset. Further tasks built upon the estimated normal vectors in the KITTI dataset show that the proposed estimator has an advantage over existing methods.
title Normal Transformer: Extracting Surface Geometry from LiDAR Points Enhanced by Visual Semantics
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2211.10580