Accurate and consistent construction of point clouds from LiDAR scanning data is fundamental for 3D modeling applications. Current solutions, such as multiview point cloud registration and LiDAR bundle adjustment, predominantly depend on the local plane assumption, which may be inadequate in complex environments lacking of planar geometries or substantial initial pose errors. To mitigate this problem, this paper presents a LiDAR bundle adjustment with progressive spatial smoothing, which is suitable for complex environments and exhibits improved convergence capabilities. The proposed method consists of a spatial smoothing module and a pose adjustment module, which combines the benefits of local consistency and global accuracy. With the spatial smoothing module, we can obtain robust and rich surface constraints employing smoothing kernels across various scales. Then the pose adjustment module corrects all poses utilizing the novel surface constraints. Ultimately, the proposed method simultaneously achieves fine poses and parametric surfaces that can be directly employed for high-quality point cloud reconstruction. The effectiveness and robustness of our proposed approach have been validated on both simulation and real-world datasets. The experimental results demonstrate that the proposed method outperforms the existing methods and achieves better accuracy in complex environments with low planar structures.
Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds
National University of Defense Technology（国防科技大学）；University of Oxford（牛津大学）
研究了三维激光雷达点云的高效目标检测问题。为了减少存储器和计算成本，现有的基于点的流水线通常采用与任务无关的随机采样或最远点采样来逐步下采样输入点云，尽管并非所有点对于目标检测的任务都同样重要。特别地，对于对象检测器，前景点固有地比背景点更重要。受此启发，我们提出了一种高效的单级基于点的3D检测器，称为IA-SSD。我们的方法的关键是利用两个可学习的，面向任务的，实例感知的下采样策略，分层选择属于感兴趣的对象的前景点。此外，我们还引入了一个上下文质心感知模块，以进一步估计精确的实例中心。最后，为了提高效率，我们按照仅编码器架构构建IA-SSD。在几个大规模检测基准上进行的大量实验证明了我们的IA-SSD的竞争力。得益于低内存占用和高并行度，它在KITTI数据集上使用单个RTX 2080 Ti GPU实现了每秒80多帧的卓越速度。代码可在\url{https://github.com/yifanzhang713/IA-SSD}上获得。
Dense-depth map guided deep Lidar-Visual Odometry with Sparse Point Clouds and Images
College of Physics and Optical Engineering, Shenzhen University（深圳大学物理与光学工程学院）；Research Institute of Tsinghua University in Shenzhen（清华大学深圳研究院）；YunJiZhiHui Engineering Co., Ltd.（云智慧工程有限公司）；Quantum Science Center of the Guangdong-Hong Kong-Macao Greater Bay Area（粤港澳大湾区量子科学中心）；State Key Laboratory of Radio Frequency Heterogeneous Integration, Shenzhen University（深圳大学射频异构集成重点实验室）；Institute of Intelligent Optical Measurement and Detection, Shenzhen University（深圳大学智能光学测量与探测研究所）
PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；College of Electronic Science and Technology, National University of Defense Technology（国防科技大学电子科学学院）
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）
Progressive Coordinate Transforms for Monocular 3D Object Detection
Fudan University（复旦大学）；Amazon Inc.（亚马逊公司）
在三维空间中识别和定位物体是人工智能智能体感知周围环境的关键能力。虽然昂贵的LiDAR点云已经取得了重大进展，但它对仅给定单目图像的3D目标检测提出了巨大挑战。虽然存在不同的替代方案来解决这个问题，但发现它们要么配备了重型网络来融合RGB和深度信息，要么在经验上无法处理数百万个伪LiDAR点。通过深入研究，我们意识到这些局限性根源于不准确的对象定位。在本文中，我们提出了一种新的和轻量级的方法，被称为{ \em渐进坐标变换}（PCT），以促进学习坐标表示。具体地，引入具有置信度感知损失的定位提升机制以逐步细化定位预测。此外，语义图像表示也被用来补偿补丁建议的使用。尽管轻量级和简单，但我们的策略在KITTI和Waymo Open Dataset单眼3D检测基准上取得了卓越的改进。与此同时，我们提出的PCT表现出很大的推广到大多数基于坐标的3D检测框架。该代码可从以下网址获取：https://github.com/amazon-research/progressive-coordinate-transforms。
Bézier Degradation Modeling for LiDAR-based Human Motion Capture
PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院精密仪器实验室，南京理工大学）；PCA Lab, School of Intelligence Science and Technology, Nanjing University（智能科学与技术学院精密仪器实验室，南京大学）
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）
A volumetric change detection framework using UAV oblique photogrammetry - A case study of ultra-high-resolution monitoring of progressive building collapse
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）
SRMambaV2: Biomimetic Attention for Sparse Point Cloud Upsampling in Autonomous Driving
College of Computer Science, Chengdu University of Information Technology（成都信息学院计算机学院）；Rice University（里士满大学）；Colorado State University（科罗拉多州立大学）；University of Colorado（科罗拉多大学）；National Research Institute for Metals（金属国家研究所）
针对自动驾驶 LiDAR 点云稀疏、距离图像重建困难的问题，本文提出 SRMambaV2，通过 2DSSA、双分支结构和 PAL 损失提升远距离区域与细粒度几何上采样效果。
