In this paper, we propose a deep learning architecture that produces accurate dense depth for the outdoor scene from a single color image and a sparse depth. Inspired by the indoor depth completion, our network estimates surface normals as the intermediate representation to produce dense depth, and can be trained end-to-end. With a modified encoder-decoder structure, our network effectively fuses the dense color image and the sparse LiDAR depth. To address outdoor specific challenges, our network predicts a confidence mask to handle mixed LiDAR signals near foreground boundaries due to occlusion, and combines estimates from the color image and surface normals with learned attention maps to improve the depth accuracy especially for distant areas. Extensive experiments demonstrate that our model improves upon the state-of-the-art performance on KITTI depth completion benchmark. Ablation study shows the positive impact of each model components to the final performance, and comprehensive analysis shows that our model generalizes well to the input with higher sparsity or from indoor scenes.
Tongji University（同济大学）；Technische Universität München（慕尼黑工业大学）；ETH Zurich（苏黎世联邦理工学院）；Westwell lab（西井实验室）
Point cloud registration is a fundamental problem in 3D computer vision. Outdoor LiDAR point clouds are typically large-scale and complexly distributed, which makes the registration challenging. In this paper, we propose an efficient hierarchical network named HRegNet for large-scale outdoor LiDAR point cloud registration. Instead of using all points in the point clouds, HRegNet performs registration on hierarchically extracted keypoints and descriptors. The overall framework combines the reliable features in deeper layer and the precise position information in shallower layers to achieve robu…
MemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory Buffers
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University（上海交通大学自动化与智能感知学院）；University of Twente（特文特大学）；University of Cambridge（剑桥大学）；University of Bath（巴斯大学）；Phigent Robotics（飞劲机器人公司）
For autonomous vehicles, high-precision real-time localization is the guarantee of stable driving. Compared with the visual odometry (VO), the LiDAR odometry (LO) has the advantages of higher accuracy and better stability. However, 2D LO is only suitable for the indoor environment, and 3D LO has less efficiency in general. Both are not suitable for the online localization of an autonomous vehicle in an outdoor driving environment. In this paper, a direct LO method based on the 2.5D grid map is proposed. The fast semi-dense direct method proposed for VO is employed to register two 2.5D maps. Ex…
Learning Geometric and Photometric Features from Panoramic LiDAR Scans for Outdoor Place Categorization
Graduate School of Information Science and Electrical Engineering, Kyushu University（九州大学信息科学与电子工程研究生院）；Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）；Faculty of Information Science and Electrical Engineering, Kyushu University（九州大学信息科学与电子工程学部）；Technical University of Cartagena（卡塔赫纳技术大学）
We propose Human-centered 4D Scene Capture (HSC4D) to accurately and efficiently create a dynamic digital world, containing large-scale indoor-outdoor scenes, diverse human motions, and rich interactions between humans and environments. Using only body-mounted IMUs and LiDAR, HSC4D is space-free without any external devices' constraints and map-free without pre-built maps. Considering that IMUs can capture human poses but always drift for long-period use, while LiDAR is stable for global localization but rough for local positions and orientations, HSC4D makes both sensors complement each other…
Chinese University of Hong Kong（香港中文大学）；ShanghaiTech University（上海科技大学）；Inceptio（嬴彻科技）；Nanyang Technological University（南洋理工大学）
State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. Although this corporation shows the competitiveness in the point cloud, it inevitably alters and abandons the 3D topology and geometric relations. A natural remedy is to utilize the3D voxelization and 3D convolution network. However, we found that in the outdoor point cloud, the improvement obtained in this way is quite limited. An important reason is the property of the outdoor point cloud, namely sparsity and varying density. Motivated…
LiDAR Based Semantic Perception for Forklifts in Outdoor Environments
Faculty of Engineering and Informatics, University of Applied Sciences Aschaffenburg（应用科学阿施芬堡大学工程与信息学院）；Linde Material Handling GmbH, Kion Group（林德物料搬运有限公司，Kion集团）
Multi-view imaging systems enable uniform coverage of 3D space and reduce the impact of occlusion, which is beneficial for 3D object detection and tracking accuracy. However, existing imaging systems built with multi-view cameras or depth sensors are limited by the small applicable scene and complicated composition. In this paper, we propose a wireless multi-view multi-modal 3D imaging system generally applicable to large outdoor scenes, which consists of a master node and several slave nodes. Multiple spatially distributed slave nodes equipped with cameras and LiDARs are connected to form a w…
Multistream Network for LiDAR and Camera-based 3D Object Detection in Outdoor Scenes
Department of Computer Science, The University of Western Australia（西澳大学计算机科学系）；School of Computing & Information Systems, The University of Melbourne（墨尔本大学计算与信息系）
Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）；ShanghaiTech University（上海科技大学）；Peking University（北京大学）；Nanyang Technological University（南洋理工大学）；University of Kentucky（肯塔基大学）
State-of-the-art methods for driving-scene LiDAR-based perception (including point cloud semantic segmentation, panoptic segmentation and 3D detection, \etc) often project the point clouds to 2D space and then process them via 2D convolution. Although this cooperation shows the competitiveness in the point cloud, it inevitably alters and abandons the 3D topology and geometric relations. A natural remedy is to utilize the 3D voxelization and 3D convolution network. However, we found that in the outdoor point cloud, the improvement obtained in this way is quite limited. An important reason is th…
This work proposes a novel motion guided method for target-less self-calibration of a LiDAR and camera and use the re-projection of LiDAR points onto the image reference frame for real-time depth upsampling. The calibration parameters are estimated by optimizing an objective function that penalizes distances between 2D and re-projected 3D motion vectors obtained from time-synchronized image and point cloud sequences. For upsampling, a simple, yet effective and time efficient formulation that minimizes depth gradients subject to an equality constraint involving the LiDAR measurements is propose…
Dahlem Center for Machine Learning and Robotics (DCMLR), Department of Mathematics and Computer Science, Freie Universität Berlin（达赫姆机器学习与机器人研究中心（DCMLR），数学与计算机科学系，柏林自由大学）
University of Waterloo（滑铁卢大学）；Chinese Academy of Sciences（中国科学院）；Jimei University（集美大学）
Semantic segmentation of large-scale outdoor point clouds is essential for urban scene understanding in various applications, especially autonomous driving and urban high-definition (HD) mapping. With rapid developments of mobile laser scanning (MLS) systems, massive point clouds are available for scene understanding, but publicly accessible large-scale labeled datasets, which are essential for developing learning-based methods, are still limited. This paper introduces Toronto-3D, a large-scale urban outdoor point cloud dataset acquired by a MLS system in Toronto, Canada for semantic segmentat…
In this paper, we evaluate eight popular and open-source 3D Lidar and visual SLAM (Simultaneous Localization and Mapping) algorithms, namely LOAM, Lego LOAM, LIO SAM, HDL Graph, ORB SLAM3, Basalt VIO, and SVO2. We have devised experiments both indoor and outdoor to investigate the effect of the following items: i) effect of mounting positions of the sensors, ii) effect of terrain type and vibration, iii) effect of motion (variation in linear and angular speed). We compare their performance in terms of relative and absolute pose error. We also provide comparison on their required computational …
Guided Model-based LiDAR Super-Resolution for Resource-Efficient Automotive scene Segmentation
Industrial Systems Institute, Athena Research Center, Patras Science Park, Greece（工业系统研究所，亚特兰蒂斯研究中心，帕特拉科学公园，希腊）；AviSense.AI, Patras Science Park, Greece（AviSense.AI，帕特拉科学公园，希腊）
L2M-Reg: Building-level Uncertainty-aware Registration of Outdoor LiDAR Point Clouds and Semantic 3D City Models
Chair of Engineering Geodesy, TUM School of Engineering and Design, Technical University of Munich（工程测量学教授会，技术大学慕尼黑工程与设计学院）；Chair of Geoinformatics, TUM School of Engineering and Design, Technical University of Munich（地理信息学教授会，技术大学慕尼黑工程与设计学院）
Most scanning LiDAR sensors generate a sequence of point clouds in real-time. While conventional 3D object detectors use a set of unordered LiDAR points acquired over a fixed time interval, recent studies have revealed that substantial performance improvement can be achieved by exploiting the spatio-temporal context present in a sequence of LiDAR point sets. In this paper, we propose a novel 3D object detection architecture, which can encode LiDAR point cloud sequences acquired by multiple successive scans. The encoding process of the point cloud sequence is performed on two different time sca…
Semantics-Guided Multimodal Masked Autoencoder Pretraining for 3D BEV Object Detection
University of Lincoln, Lincoln Centre for Autonomous Systems（林肯大学，林肯自主系统中心）；University of Cambridge, Institute for Manufacturing, Department of Engineering（剑桥大学，制造研究所，工程系）
University of Manchester（曼彻斯特大学）；Intel Corporation（英特尔公司）
LiDAR provides highly accurate 3D point clouds. However, data needs to be manually labelled in order to provide subsequent useful information. Manual annotation of such data is time consuming, tedious and error prone, and hence in this paper we present three automatic methods for annotating trees in LiDAR data. The first method requires high density point clouds and uses certain LiDAR data attributes for the purpose of tree identification, achieving almost 90% accuracy. The second method uses a voxel-based 3D Convolutional Neural Network on low density LiDAR datasets and is able to identify mo…
Monocular 3D object detection is a challenging task in the self-driving and computer vision community. As a common practice, most previous works use manually annotated 3D box labels, where the annotating process is expensive. In this paper, we find that the precisely and carefully annotated labels may be unnecessary in monocular 3D detection, which is an interesting and counterintuitive finding. Using rough labels that are randomly disturbed, the detector can achieve very close accuracy compared to the one using the ground-truth labels. We delve into this underlying mechanism and then empirica…
PVNet: Point-Voxel Interaction LiDAR Scene Upsampling Via Diffusion Models
Telecom Guizhou Branch（贵州电信支局）；School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）；College of Engineering, Huaqiao University（华侨大学工程学院）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）；Bio-Computing Research Center, Shenzhen Graduate School, Harbin Institute of Technology（哈尔滨工业大学深圳研究生院生物计算研究中心）；Key Laboratory of Network Oriented Intelligent Computation（网络导向智能计算重点实验室）
UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase
Shanghai AI Laboratory（上海人工智能实验室）；Hochschule Bremerhaven（不来梅应用技术大学）；The University of Hong Kong（香港大学）；East China Normal University（华东师范大学）；National University of Singapore（新加坡国立大学）；Fudan University（复旦大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai Tech University（上海科技大学）
T2LDM++: A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation
School of Computer Science and Engineering（计算机科学与工程学院）；Nanjing University of Science and Technology（南京理工大学）；Faculty of Data Science（数据科学学院）；City University of Macau（澳门城市大学）；Beijing Institute of Technology（北京理工大学）；Fondazione Bruno Kessler（布鲁诺·凯瑟尔基金会）；School of Public Health（公共卫生学院）；Shanghai Jiao Tong University（上海交通大学）；School of Computing（计算机学院）；National University of Singapore（新加坡国立大学）
At present, the anchor-based or anchor-free models that use LiDAR point clouds for 3D object detection use the center assigner strategy to infer the 3D bounding boxes. However, in a real world scene, the LiDAR can only acquire a limited object surface point clouds, but the center point of the object does not exist. Obtaining the object by aggregating the incomplete surface point clouds will bring a loss of accuracy in direction and dimension estimation. To address this problem, we propose a corner-guided anchor-free single-stage 3D object detection model (CG-SSD ).Firstly, 3D sparse convolutio…
Paris-CARLA-3D is a dataset of several dense colored point clouds of outdoor environments built by a mobile LiDAR and camera system. The data are composed of two sets with synthetic data from the open source CARLA simulator (700 million points) and real data acquired in the city of Paris (60 million points), hence the name Paris-CARLA-3D. One of the advantages of this dataset is to have simulated the same LiDAR and camera platform in the open source CARLA simulator as the one used to produce the real data. In addition, manual annotation of the classes using the semantic tags of CARLA was perfo…
