The proposed RMS-FlowNet++ is a novel end-to-end learning-based architecture for accurate and efficient scene flow estimation that can operate on high-density point clouds. For hierarchical scene f low estimation, existing methods rely on expensive Farthest-Point-Sampling (FPS) to sample the scenes, must find large correspondence sets across the consecutive frames and/or must search for correspondences at a full input resolution. While this can improve the accuracy, it reduces the overall efficiency of these methods and limits their ability to handle large numbers of points due to memory requirements. In contrast to these methods, our architecture is based on an efficient design for hierarchical prediction of multi-scale scene flow. To this end, we develop a special flow embedding block that has two advantages over the current methods: First, a smaller correspondence set is used, and second, the use of Random-Sampling (RS) is possible. In addition, our architecture does not need to search for correspondences at a full input resolution. Exhibiting high accuracy, our RMS-FlowNet++ provides a faster prediction than state-of-the-art methods, avoids high memory requirements and enables efficient scene flow on dense point clouds of more than 250K points at once. Our comprehensive experiments verify the accuracy of RMS FlowNet++ on the established FlyingThings3D data set with different point cloud densities and validate our design choices. Furthermore, we demonstrate that our model has a competitive ability to generalize to the real-world scenes of the KITTI data set without fine-tuning.
HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds
Stanford University(斯坦福大学);University of California, Davis(加州大学戴维斯分校);TuSimple(图森未来)
我们提出了一种新的深度神经网络架构,用于直接对大规模3D点云进行端到端场景流估计。受双边卷积层(BCL)的启发,我们提出了新的DownBCL,UpBCL和CorrBCL操作,从非结构化点云恢复结构信息,并融合来自两个连续点云的信息。操作离散和稀疏的permutohedral格点,我们的架构设计是节俭的计算成本。我们的模型可以有效地处理一对点云帧,每帧最多86K个点。我们的方法在FlyingThings3D和KITTI Scene Flow 2015数据集上实现了最先进的性能。此外,在合成数据上训练,我们的方法对真实世界的数据和不同的点密度表现出很强的泛化能力,而无需微调。
EvTrajGS: Accurate and Efficient 3D Gaussian Splatting from Unposed Event Streams
School of Computer Science and Engineering, Sun Yat-sen University(中山大学计算机科学与工程学院);Guangdong Province Key Laboratory of Information Security Technology(广东省信息安全技术重点实验室);Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education(机器智能与先进计算教育部重点实验室);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);School of Computing and Information Technology, Great Bay University(大湾区大学计算与信息技术学院)
ST-FlowNet: An Efficient Spiking Neural Network for Event-Based Optical Flow Estimation
Clinical Hospital of Chengdu Brain Science Institute(成都脑科学研究院临床医院);MOE Key Lab for NeuroInformation(教育部神经信息关键实验室);China-Cuba Belt and Road Joint Laboratory on Neurotechnology and Brain-Apparatus Communication(中 cuba 带路神经技术与脑-装置通信联合实验室);School of Life Science and Technology, University of Electronic Science and Technology of China(电子科技大学生命科学与技术学院);School of Artificial Intelligence, Chongqing University of Education(重庆教育学院人工智能学院);Sichuan Academy of Medical Sciences and Sichuan Provincial People’s Hospital(四川省医学科学院和四川省人民医院);Research Unit of NeuroInformation (2019RU035), Chinese Academy of Medical Sciences(神经信息研究单位(2019RU035),中国医学科学院)
Monocular Depth Guided Occlusion-Aware Disparity Refinement via Semi-supervised Learning in Laparoscopic Images
School of Life Science and Technology, Harbin Institute of Technology(生命科学与技术学院,哈尔滨工业大学);State Key Laboratory of Robotics and System, Harbin Institute of Technology(机器人与系统国家重点实验室,哈尔滨工业大学)
M^3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM
Shanghai Jiao Tong University(上海交通大学);Shanghai Artificial Intelligence Laboratory(上海人工智能实验室);Fudan University(复旦大学);Shanghai Innovation Institute(上海创新研究院);Zhejiang University(浙江大学);Beijing Institute of Technology(北京理工大学);The Chinese University of Hong Kong(香港中文大学);The University of Hong Kong(香港大学)
CMAMBADEPTH: Self-supervised Monocular Depth Estimation with Channel Mamba and Hybrid Attention
Harbin Engineering University(哈尔滨工程大学);Key Laboratory of Advanced Marine Communication and Information Technology(先进海洋通信与信息技术重点实验室);University of Toronto(多伦多大学);Kanagawa University(神奈川大学)
SenseTime Research(商汤科技研究院);Qing Yuan Research Institute, Shanghai Jiao Tong University(上海交通大学清源研究院);Nanjing University of Science and Technology(南京理工大学);School of Software Engineering, Xi’an Jiaotong University(西安交通大学软件学院)
MMD-SLAM: Structure-Enhanced Multi-Meta Gaussian Distribution-Guided Visual SLAM
HFIPS, Chinese Academy of Sciences(中国科学院合肥物质科学研究院);University of Science and Technology of China(中国科学技术大学);Aarhus University(奥胡斯大学);University of Tokyo(东京大学);Beijing University of Chemical Technology(北京化工大学);North China Electric Power University(华北电力大学)
NSL-SLAM: High-Fidelity Neural Structured-Light Depth for Practical SLAM and Reconstruction
Wangxuan Institute of Computer Technology, Peking University(北京大学王选计算机研究所);School of Computer Science and Technology, Beihang University(北京航空航天大学计算机科学与技术学院);Yuanpei College, Peking University(北京大学元培学院)
RaCalNet: Radar Calibration Network for Sparse-Supervised Metric Depth Estimation
School of Automation and Intelligent Sensing, Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai 200240, China(上海交通大学自动化与智能感知学院,医学机器人研究所);School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China(上海交通大学数学科学学院);South China University of Technology, Guangzhou, China(华南理工大学);State Grid Intelligence Technology CO., LTD(国家电网智能技术有限公司)
Absolute distance prediction based on deep learning object detection and monocular depth estimation models
DEIM, Rovira i Virgili University(罗维拉·维尔吉利大学)
通过使用立体相机或3D相机估计深度图像,从2D图像确定场景中的对象与相机传感器之间的距离是可行的。深度估计的结果是相对距离,其可用于计算在现实中适用的绝对距离。然而,使用2D单目相机进行距离估计是非常具有挑战性的。本文提出了一个深度学习框架,该框架由两个深度网络组成,用于使用单个图像进行深度估计和目标检测。首先,使用You Only Look Once(YOLOv5)网络检测和定位场景中的对象。并行地,使用深度自动编码器网络来计算估计的深度图像以检测相对距离。提出的基于目标检测的YOLO是使用监督学习技术训练的,反过来,深度估计网络是自监督训练的。在室外场景的真实图像上对所提出的距离估计框架进行了评估。结果表明,该框架是有前途的,它产生了96%的准确性与RMSE的0.203的正确的绝对距离。
Robust and Precise Vehicle Localization based on Multi-sensor Fusion in Diverse City Scenes
Baidu Autonomous Driving Business Unit(百度自动驾驶业务部)
我们提出了一个强大的和精确的定位系统,实现厘米级的定位精度在不同的城市场景。我们的系统自适应地使用来自GNSS、LiDAR和IMU等互补传感器的信息,以在具有挑战性的场景(如市区、高速公路和隧道)中实现高定位精度和弹性。我们不只是依赖于LiDAR强度或3D几何形状,而是创新性地使用LiDAR强度和高度线索,以显着提高定位系统的准确性和鲁棒性。我们的GNSS RTK模块利用多传感器融合框架的帮助,实现了更好的模糊度解决成功率。采用一种误差状态卡尔曼滤波器对不同来源的定位测量值进行融合,并对融合后的定位测量值进行新的不确定性估计。我们详细验证了我们方法的有效性,实现了5- 10 cm RMS精度,并优于以前最先进的系统。重要的是,我们的系统在部署在大型自动驾驶车队中时,使我们的车辆在拥挤的城市街道上完全自动驾驶,尽管道路建设时有发生。一个数据集,包括超过60公里的实际交通驾驶在不同的城市道路被用来全面测试我们的系统。
State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University(测绘遥感信息工程国家重点实验室,武汉大学);Electronic Information School, Wuhan University(电子信息学院,武汉大学)