Leveraging recent diffusion models, LiDAR-based large-scale 3D scene generation has achieved great success. While recent voxel-based approaches can generate both geometric structures and semantic labels, existing range-view methods are limited to producing unlabeled LiDAR scenes. Relying on pretrained segmentation models to predict the semantic maps often results in suboptimal cross-modal consistency. To address this limitation while preserving the advantages of range-view representations, such as computational efficiency and simplified network design, we propose Spiral, a novel range-view LiDAR diffusion model that simultaneously generates depth, reflectance images, and semantic maps. Furthermore, we introduce novel semantic-aware metrics to evaluate the quality of the generated labeled range-view data. Experiments on the SemanticKITTI and nuScenes datasets demonstrate that Spiral achieves state-of-the-art performance with the smallest parameter size, outperforming two-step methods that combine the generative and segmentation models. Additionally, we validate that range images generated by Spiral can be effectively used for synthetic data augmentation in the downstream segmentation training, significantly reducing the labeling effort on LiDAR data.
UBTECH Sydney Artificial Intelligence Centre（优必选悉尼人工智能中心）；University of Sydney（悉尼大学）；University of Technology Sydney（悉尼科技大学）；Hangzhou Dianzi University（杭州电子科技大学）
Despite rapid developments in visual image-based road detection, robustly identifying road areas in visual images remains challenging due to issues like illumination changes and blurry images. To this end, LiDAR sensor data can be incorporated to improve the visual image-based road detection, because LiDAR data is less susceptible to visual noises. However, the main difficulty in introducing LiDAR information into visual image-based road detection is that LiDAR data and its extracted features do not share the same space with the visual data and visual features. Such gaps in spaces may limit th…
One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception
Shanghai Jiao Tong University（上海交通大学）；Ningbo Institute of Digital Twin, Eastern Institute of Technology（宁波数字孪生研究院，东方理工）；Tokyo Institute of Technology（东京工业大学）；PhiGent Robotics（PhiGent机器人公司）
Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment. While significant progress has been achieved with expensive LiDAR point clouds, it poses a great challenge for 3D object detection given only a monocular image. While there exist different alternatives for tackling this problem, it is found that they are either equipped with heavy networks to fuse RGB and depth information or empirically ineffective to process millions of pseudo-LiDAR points. With in-depth examination, we realize that these limitations are rooted in …
The Chinese University of Hong Kong（香港中文大学）；ShanghaiTech University（上海科技大学）；SenseTime Research（商汤科技研究院）
State-of-the-art methods for large-scale driving-scene LiDAR semantic segmentation often project and process the point clouds in the 2D space. The projection methods includes spherical projection, bird-eye view projection, etc. Although this process makes the point cloud suitable for the 2D CNN-based networks, it inevitably alters and abandons the 3D topology and geometric relations. A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space. In this work, we first perform an in-depth analysis for different repr…
Learning to Expand Images for Efficient Visual Autoregressive Modeling
University of Electronic Science and Technology of China（电子科技大学）；School of Computer Science and Engineering, Central South University（中南大学计算机科学与工程学院）；Xidian University（西安电子科技大学）；SenseTime Research（商汤科技研究院）；Shanghai Jiao Tong University（上海交通大学）
Autonomous driving (AD) datasets have progressively grown in size in the past few years to enable better deep representation learning. Active learning (AL) has re-gained attention recently to address reduction of annotation costs and dataset size. AL has remained relatively unexplored for AD datasets, especially on point cloud data from LiDARs. This paper performs a principled evaluation of AL based dataset distillation on (1/4th) of the large Semantic-KITTI dataset. Further on, the gains in model performance due to data augmentation (DA) are demonstrated across different subsets of the AL loo…
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…
Unlocking Generalization Power in LiDAR Point Cloud Registration
School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）；Ningbo Institute, Northwestern Polytechnical University（西北工业大学宁波研究院）；Swansea University（斯旺西大学）；HuaZhong University of Science and Technology（华中科技大学）
DriveExplorer: Images-Only Decoupled 4D Reconstruction with Progressive Restoration for Driving View Extrapolation
Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology（广东省级超高清沉浸媒体技术重点实验室）；School of Electronic and Computer Engineering（电子与计算机工程学院）；Shenzhen Graduate School, Peking University（北京大学深圳研究生院）
Vision-Driven 2D Supervised Fine-Tuning Framework for Bird's Eye View Perception
School of Vehicle and Mobility, Tsinghua University（清华大学车辆与 Mobility学院）；State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University（清华大学智能绿色车辆与交通全国重点实验室）
University of Minnesota--Twin Cities（明尼苏达大学双城分校）；University of Virginia（弗吉尼亚大学）
We propose a technique to develop (and localize in) topological maps from light detection and ranging (Lidar) data. Localizing an autonomous vehicle with respect to a reference map in real-time is crucial for its safe operation. Owing to the rich information provided by Lidar sensors, these are emerging as a promising choice for this task. However, since a Lidar outputs a large amount of data every fraction of a second, it is progressively harder to process the information in real-time. Consequently, current systems have migrated towards faster alternatives at the expense of accuracy. To overc…
Progressive Depth Decoupling and Modulating for Flexible Depth Completion
School of Automation, Hangzhou Dianzi University（杭州电子科技大学自动化学院）；School of Software Engineering, Xi’an Jiaotong University（西安交通大学软件学院）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；School of Communication Engineering, Hangzhou Dianzi University（杭州电子科技大学通信工程学院）；Lishui Institute of Hangzhou Dianzi University（杭州电子科技大学丽水研究院）
UniScene: Unified Occupancy-centric Driving Scene Generation
Shanghai Jiao Tong University（上海交通大学）；Ningbo Institute of Digital Twin, Eastern Institute of Technology（东方理工大学宁波数字孪生研究院）；Tsinghua University（清华大学）；MEGVII Technology（旷视科技）；Mach Drive（马赫驱动）；Fudan University（复旦大学）；University of Hong Kong（香港大学）
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；PhiGent Robotics（鉴智机器人）；University of Chinese Academy of Sciences（中国科学院大学）
BEV perception is of great importance in the field of autonomous driving, serving as the cornerstone of planning, controlling, and motion prediction. The quality of the BEV feature highly affects the performance of BEV perception. However, taking the noises in camera parameters and LiDAR scans into consideration, we usually obtain BEV representation with harmful noises. Diffusion models naturally have the ability to denoise noisy samples to the ideal data, which motivates us to utilize the diffusion model to get a better BEV representation. In this work, we propose an end-to-end framework, nam…
CurriFlow: Curriculum-Guided Depth Fusion with Optical Flow-Based Temporal Alignment for 3D Semantic Scene Completion
School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院）；Ministry of Education（教育部）；Shandong Computer Science Center (National Supercomputer Center in Jinan)（山东省计算机科学中心（济南国家超算中心））；Qilu University of Technology (Shandong Academy of Sciences)（齐鲁工业大学（山东省科学院））；Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing（山东省计算电力互联网与服务计算重点实验室）；Shandong Fundamental Research Center for Computer Science（山东省计算机科学基础研究中心）
