In this study, we address a gap in existing unsupervised domain adaptation approaches on LiDAR-based 3D object detection, which have predominantly concentrated on adapting between established, high-density autonomous driving datasets. We focus on sparser point clouds, capturing scenarios from different perspectives: not just from vehicles on the road but also from mobile robots on sidewalks, which encounter significantly different environmental conditions and sensor configurations. We introduce Unsupervised Adversarial Domain Adaptation for 3D Object Detection (UADA3D). UADA3D does not depend on pre-trained source models or teacher-student architectures. Instead, it uses an adversarial approach to directly learn domain-invariant features. We demonstrate its efficacy in various adaptation scenarios, showing significant improvements in both self-driving car and mobile robot domains. Our code is open-source and will be available soon.
Scene understanding is a pivotal task for autonomous vehicles to safely navigate in the environment. Recent advances in deep learning enable accurate semantic reconstruction of the surroundings from LiDAR data. However, these models encounter a large domain gap while deploying them on vehicles equipped with different LiDAR setups which drastically decreases their performance. Fine-tuning the model for every new setup is infeasible due to the expensive and cumbersome process of recording and manually labeling new data. Unsupervised Domain Adaptation (UDA) techniques are thus essential to fill t…
In this paper, we focus on a less explored, but more realistic and complex problem of domain adaptation in LiDAR semantic segmentation. There is a significant drop in performance of an existing segmentation model when training (source domain) and testing (target domain) data originate from different LiDAR sensors. To overcome this shortcoming, we propose an unsupervised domain adaptation framework that leverages unlabeled target domain data for self-supervision, coupled with an unpaired mask transfer strategy to mitigate the impact of domain shifts. Furthermore, we introduce the gated adapter …
Recently, learning-based ego-motion estimation approaches have drawn strong interest from studies mostly focusing on visual perception. These groundbreaking works focus on unsupervised learning for odometry estimation but mostly for visual sensors. Compared to images, a learning-based approach using Light Detection and Ranging (LiDAR) has been reported in a few studies where, most often, a supervised learning framework is proposed. In this paper, we propose a novel approach to geometry-aware deep LiDAR odometry trainable via both supervised and unsupervised frameworks. We incorporate the Itera…
LIDAR has become an important part of many autonomous vehicles with its advantages on distance measurement and obstacle detection. LIDAR produces point clouds which have important information about surrounding environment. In this paper, we collected trajectory data on a two lane urban road using a Velodyne VLP-16 Lidar. Due to dynamic nature of data collection and limited range of the sensor, some of these trajectories have missing points or gaps. In this paper, we propose a novel method for recovery of missing vehicle trajectory data points using microscopic traffic flow models. While short …
ShanghaiTech University（上海科技大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程技术研究中心）；The Chinese University of Hong Kong（香港中文大学）
Domain adaptation for Cross-LiDAR 3D detection is challenging due to the large gap on the raw data representation with disparate point densities and point arrangements. By exploring domain-invariant 3D geometric characteristics and motion patterns, we present an unsupervised domain adaptation method that overcomes above difficulties. First, we propose the Spatial Geometry Alignment module to extract similar 3D shape geometric features of the same object class to align two domains, while eliminating the effect of distinct point distributions. Second, we present Temporal Motion Alignment module …
University of Trento（特伦托大学）；LTCI, Télécom Paris, Institut Polytechnique de Paris（巴黎理工学院巴黎电信学院LTCI实验室）；Huawei Research（华为研究院）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；Sapienza University of Rome（罗马第一大学）
3D object detectors based only on LiDAR point clouds hold the state-of-the-art on modern street-view benchmarks. However, LiDAR-based detectors poorly generalize across domains due to domain shift. In the case of LiDAR, in fact, domain shift is not only due to changes in the environment and in the object appearances, as for visual data from RGB cameras, but is also related to the geometry of the point clouds (e.g., point density variations). This paper proposes SF-UDA$^{3D}$, the first Source-Free Unsupervised Domain Adaptation (SF-UDA) framework to domain-adapt the state-of-the-art PointRCNN …
CO^3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving
The University of Hong Kong（香港大学）；Shanghai AI Laboratory（上海人工智能实验室）；Huawei Noah’s Ark Lab（华为诺亚实验室）；The Chinese University of Hong Kong（香港中文大学）；Hong Kong University of Science and Technology（香港科技大学）
Earlier work demonstrates the promise of deep-learning-based approaches for point cloud segmentation; however, these approaches need to be improved to be practically useful. To this end, we introduce a new model SqueezeSegV2 that is more robust to dropout noise in LiDAR point clouds. With improved model structure, training loss, batch normalization and additional input channel, SqueezeSegV2 achieves significant accuracy improvement when trained on real data. Training models for point cloud segmentation requires large amounts of labeled point-cloud data, which is expensive to obtain. To sideste…
University of Southern California（南加州大学）；Waymo, LLC（Waymo公司）
In autonomous driving, a LiDAR-based object detector should perform reliably at different geographic locations and under various weather conditions. While recent 3D detection research focuses on improving performance within a single domain, our study reveals that the performance of modern detectors can drop drastically cross-domain. In this paper, we investigate unsupervised domain adaptation (UDA) for LiDAR-based 3D object detection. On the Waymo Domain Adaptation dataset, we identify the deteriorating point cloud quality as the root cause of the performance drop. To address this issue, we pr…
Segmentation of lidar data is a task that provides rich, point-wise information about the environment of robots or autonomous vehicles. Currently best performing neural networks for lidar segmentation are fine-tuned to specific datasets. Switching the lidar sensor without retraining on a big set of annotated data from the new sensor creates a domain shift, which causes the network performance to drop drastically. In this work we propose a new method for lidar domain adaption, in which we use annotated panoptic lidar datasets and recreate the recorded scenes in the structure of a different lida…
DiffSSC: Semantic LiDAR Scan Completion using Denoising Diffusion Probabilistic Models
Autonomous Intelligent Systems group, Computer Science Institute VI – Intelligent Systems and Robotics – and the Center for Robotics and the Lamarr Institute for Machine Learning and Artificial Intelligence, University of Bonn, Germany（自主智能系统组，计算机科学研究所VI——智能系统与机器人——和机器人中心以及拉马尔人工智能与机器学习研究所，波恩大学，德国）
Indian Institute of Science（印度科学研究所）；AMIDC Pvt Ltd（AMIDC私人有限公司）；Chennai Mathematical Institute（钦奈数学研究所）
Accurate reconstruction of static environments from LiDAR scans of scenes containing dynamic objects, which we refer to as Dynamic to Static Translation (DST), is an important area of research in Autonomous Navigation. This problem has been recently explored for visual SLAM, but to the best of our knowledge no work has been attempted to address DST for LiDAR scans. The problem is of critical importance due to wide-spread adoption of LiDAR in Autonomous Vehicles. We show that state-of the art methods developed for the visual domain when adapted for LiDAR scans perform poorly. We develop DSLR, a…
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 int…
LiDAR semantic segmentation provides 3D semantic information about the environment, an essential cue for intelligent systems during their decision making processes. Deep neural networks are achieving state-of-the-art results on large public benchmarks on this task. Unfortunately, finding models that generalize well or adapt to additional domains, where data distribution is different, remains a major challenge. This work addresses the problem of unsupervised domain adaptation for LiDAR semantic segmentation models. Our approach combines novel ideas on top of the current state-of-the-art approac…
Mines Paris - PSL, PSL University（巴黎国立高等矿业学校-PSL，PSL大学）；ENSTA Paris, Institut Polytechnique de Paris（巴黎国立高等先进技术学校，巴黎理工学院）
Transfer learning is a proven technique in 2D computer vision to leverage the large amount of data available and achieve high performance with datasets limited in size due to the cost of acquisition or annotation. In 3D, annotation is known to be a costly task; nevertheless, pre-training methods have only recently been investigated. Due to this cost, unsupervised pre-training has been heavily favored. In this work, we tackle the case of real-time 3D semantic segmentation of sparse autonomous driving LiDAR scans. Such datasets have been increasingly released, but each has a unique label set. We…
University of Trento（特伦托大学）；Sapienza University of Rome（罗马第一大学）；NVIDIA AI Technology Center（英伟达人工智能技术中心）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
3D LiDAR semantic segmentation is fundamental for autonomous driving. Several Unsupervised Domain Adaptation (UDA) methods for point cloud data have been recently proposed to improve model generalization for different sensors and environments. Researchers working on UDA problems in the image domain have shown that sample mixing can mitigate domain shift. We propose a new approach of sample mixing for point cloud UDA, namely Compositional Semantic Mix (CoSMix), the first UDA approach for point cloud segmentation based on sample mixing. CoSMix consists of a two-branch symmetric network that can …
Domain gaps of sensor modalities pose a challenge for the design of autonomous robots. Taking a step towards closing this gap, we propose two unsupervised training frameworks for finding a common representation of LiDAR and camera data. The first method utilizes a double Siamese training structure to ensure consistency in the results. The second method uses a Canny edge image guiding the networks towards a desired representation. All networks are trained in an unsupervised manner, leaving room for scalability. The results are evaluated using common computer vision applications, and the limitat…
With the convenient availability of remote sensing data, how to make models to interpret complex remote sensing data attracts wide attention. In remote sensing data, hyperspectral images contain spectral information and LiDAR contains elevation information. Hence, more explorations are warranted to better fuse the features of different source data. In this paper, we introduce semantic understanding to dynamically fuse data from two different sources, extract features of HSI and LiDAR through different capsule network branches and improve self-supervised loss and random rigid rotation in Canoni…
Hong Kong University of Science and Technology（香港科技大学）
Autonomous driving in urban crowds at unregulated intersections is challenging, where dynamic occlusions and uncertain behaviors of other vehicles should be carefully considered. Traditional methods are heuristic and based on hand-engineered rules and parameters, but scale poorly in new situations. Therefore, they require high labor cost to design and maintain rules in all foreseeable scenarios. Recently, deep reinforcement learning (DRL) has shown promising results in urban driving scenarios. However, DRL is known to be sample inefficient, and most previous works assume perfect observations s…
In this paper we address the challenging problem of domain adaptation in LiDAR semantic segmentation. We consider the setting where we have a fully-labeled data set from source domain and a target domain with a few labeled and many unlabeled examples. We propose a domain adaption framework that mitigates the issue of domain shift and produces appealing performance on the target domain. To this end, we develop a GAN-based image-to-image translation engine that has generators with alternating connections, and couple it with a state-of-the-art LiDAR semantic segmentation network. Our framework is…
Nanjing University of Science and Technology（南京理工大学）；PCA Lab（PCA实验室）
Extensive research efforts have been dedicated to deep learning based odometry. Nonetheless, few efforts are made on the unsupervised deep lidar odometry. In this paper, we design a novel framework for unsupervised lidar odometry with the IMU, which is never used in other deep methods. First, a pair of siamese LSTMs are used to obtain the initial pose from the linear acceleration and angular velocity of IMU. With the initial pose, we perform the rigid transform on the current frame and align it closer to the last frame. Then, we extract vertex and normal features from the transformed point clo…
Northwestern Polytechnical University（西北工业大学）；Australian National University（澳大利亚国立大学）；ACRV；Data61 CSIRO（联邦科学与工业研究组织Data61）；NEC Laboratories America（NEC美国实验室）
In this paper, we present LidarStereoNet, the first unsupervised Lidar-stereo fusion network, which can be trained in an end-to-end manner without the need of ground truth depth maps. By introducing a novel "Feedback Loop'' to connect the network input with output, LidarStereoNet could tackle both noisy Lidar points and misalignment between sensors that have been ignored in existing Lidar-stereo fusion studies. Besides, we propose to incorporate a piecewise planar model into network learning to further constrain depths to conform to the underlying 3D geometry. Extensive quantitative and qualit…
NTT Human Informatics Laboratories（NTT人类信息学实验室）；NTT Communication Science Laboratories（NTT通信科学实验室）
Intrinsic image decomposition (IID) is the task that decomposes a natural image into albedo and shade. While IID is typically solved through supervised learning methods, it is not ideal due to the difficulty in observing ground truth albedo and shade in general scenes. Conversely, unsupervised learning methods are currently underperforming supervised learning methods since there are no criteria for solving the ill-posed problems. Recently, light detection and ranging (LiDAR) is widely used due to its ability to make highly precise distance measurements. Thus, we have focused on the utilization…
Data-driven Camera and Lidar Simulation Models for Autonomous Driving: A Review from Generative Models to Volume Renderers
WMG, University of Warwick（华威大学WMG学院）；School of Electronics, Electrical Engineering and Computer Science at Queen’s University of Belfast（贝尔法斯特女王大学电子、电气工程与计算机科学学院）
High-precision lidar odomety is an essential part of autonomous driving. In recent years, deep learning methods have been widely used in lidar odomety tasks, but most of the current methods only extract the global features of the point clouds. It is impossible to obtain more detailed point-level features in this way. In addition, only the fully connected layer is used to estimate the pose. The fully connected layer has achieved obvious results in the classification task, but the changes in pose are a continuous rather than discrete process, high-precision pose estimation can not be obtained on…
Telekooperation Lab, Technical University Darmstadt（达姆施塔特工业大学远程协作实验室）
In this work, we address the problem of unsupervised moving object segmentation (MOS) in 4D LiDAR data recorded from a stationary sensor, where no ground truth annotations are involved. Deep learning-based state-of-the-art methods for LiDAR MOS strongly depend on annotated ground truth data, which is expensive to obtain and scarce in existence. To close this gap in the stationary setting, we propose a novel 4D LiDAR representation based on multivariate time series that relaxes the problem of unsupervised MOS to a time series clustering problem. More specifically, we propose modeling the change…
TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception
The University of Hong Kong（香港大学）；Yale University（耶鲁大学）；Shanghai AI Laboratory（上海人工智能实验室）；HKU Shanghai Intelligent Computing Research Center（香港大学上海智能计算研究中心）
Australian Centre for Field Robotics（澳大利亚现场机器人中心）；University of Sydney（悉尼大学）；Baraja Pty Ltd（巴拉哈私人有限公司）
Every autonomous driving dataset has a different configuration of sensors, originating from distinct geographic regions and covering various scenarios. As a result, 3D detectors tend to overfit the datasets they are trained on. This causes a drastic decrease in accuracy when the detectors are trained on one dataset and tested on another. We observe that lidar scan pattern differences form a large component of this reduction in performance. We address this in our approach, SEE-VCN, by designing a novel viewer-centred surface completion network (VCN) to complete the surfaces of objects of intere…
The ability of scene understanding has sparked active research for panoramic image semantic segmentation. However, the performance is hampered by distortion of the equirectangular projection (ERP) and a lack of pixel-wise annotations. For this reason, some works treat the ERP and pinhole images equally and transfer knowledge from the pinhole to ERP images via unsupervised domain adaptation (UDA). However, they fail to handle the domain gaps caused by: 1) the inherent differences between camera sensors and captured scenes; 2) the distinct image formats (e.g., ERP and pinhole images). In this pa…
Benchmarking individual tree segmentation using multispectral airborne laser scanning data: the FGI-EMIT dataset
Finnish Geospatial Research Institute FGI（芬兰地理空间研究 institute）；The National Land Survey of Finland（芬兰国家土地调查局）；Department of Remote Sensing and Photogrammetry（遥感与摄影测量系）；Department of Built Environment, School of Engineering, Aalto University（环境学院，工程学院，阿alto大学）
Depth perception is pivotal in many fields, such as robotics and autonomous driving, to name a few. Consequently, depth sensors such as LiDARs rapidly spread in many applications. The 3D point clouds generated by these sensors must often be coupled with an RGB camera to understand the framed scene semantically. Usually, the former is projected over the camera image plane, leading to a sparse depth map. Unfortunately, this process, coupled with the intrinsic issues affecting all the depth sensors, yields noise and gross outliers in the final output. Purposely, in this paper, we propose an effec…
Graz University of Technology（格拉茨工业大学）；Christian Doppler Laboratory for Embedded Machine Learning（克里斯蒂安·多普勒嵌入式机器学习实验室）
LiDAR 3D object detection models are inevitably biased towards their training dataset. The detector clearly exhibits this bias when employed on a target dataset, particularly towards object sizes. However, object sizes vary heavily between domains due to, for instance, different labeling policies or geographical locations. State-of-the-art unsupervised domain adaptation approaches outsource methods to overcome the object size bias. Mainstream size adaptation approaches exploit target domain statistics, contradicting the original unsupervised assumption. Our novel unsupervised anchor calibratio…
