CMG-Net: Robust Normal Estimation for Point Clouds via Chamfer Normal Distance and Multi-scale Geometry
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences(中国科学院香港创新研究院);SenseTime Research(商汤科技研究院);Soochow University(苏州大学)
本研究提出了一种精确且鲁棒的点云法线估计方法。现有方法直接最小化标注法线与预测法线间的偏差,易导致方向不一致问题,对此我们首先提出名为Chamfer Normal Distance(Chamfer法线距离)的新指标来解决该问题。该指标不仅缓解了这一挑战,还能促进网络训练,大幅提升网络抗噪声鲁棒性。随后,我们设计了一种创新架构,包含Multi-scale Local Feature Aggregation(多尺度局部特征聚合)与Hierarchical Geometric Information Fusion(分层几何信息融合),使网络能更有效地捕捉复杂几何细节,缓解尺度选择的模糊性。大量实验表明,我们的方法在合成数据集与真实数据集上均达到了SOTA(当前最优)性能,在受噪声污染的场景中表现尤为突出。代码已开源至https://github.com/YingruiWoo/CMG-Net_Pytorch。
英文摘要:
This work presents an accurate and robust method for estimating normals from point clouds. In contrast to predecessor approaches that minimize the deviations between the annotated and the predicted normals directly, leading to direction inconsistency, we first propose a new metric termed Chamfer Normal Distance to address this issue. This not only mitigates the challenge but also facilitates network training and substantially enhances the network robustness against noise. Subsequently, we devise an innovative architecture that encompasses Multi-scale Local Feature Aggregation and Hierarchical Geometric Information Fusion. This design empowers the network to capture intricate geometric details more effectively and alleviate the ambiguity in scale selection. Extensive experiments demonstrate that our method achieves the state-of-the-art performance on both synthetic and real-world datasets, particularly in scenarios contaminated by noise. Our implementation is available at https://github.com/YingruiWoo/CMG-Net_Pytorch.
OCMG-Net: Neural Oriented Normal Refinement for Unstructured Point Clouds
Institute of Automation, CAS(中国科学院自动化研究所);Hong Kong Institute of Science & Innovation Chinese Academy of Sciences(中国科学院香港创新研究院);Academy of Mathematics and Systems Science, CAS(中国科学院数学与系统科学研究院)
OCMG-Net提出一种点云定向法线精化框架,通过特征空间符号定向与数据增强、Chamfer Normal Distance度量及双并行架构,在效率与精度间取得平衡并提升抗噪性。
Super-Resolution of Airborne Laser Scanning Point Clouds for Forest Inventory
Department of Forestry and Natural Resources, Purdue University(林业与自然资源系,普渡大学);Lyles School of Civil and Construction Engineering, Purdue University(莱尔斯土木与建设工程学院,普渡大学)
本文提出3D Forest Super Resolution模型,通过提升点云密度和减少噪声,提高森林调查精度,实验表明其在树干定位和直径估计上表现优异。
MinCD-PnP: Learning 2D-3D Correspondences with Approximate Blind PnP
Huazhong University of Science and Technology, China(华中科技大学);Northwestern Polytechnical University, China(西北工业大学);McMaster University, Canada(麦马士威大学);Delft University of Technology, Netherlands(代尔夫特理工大学)
3D Brain Reconstruction by Hierarchical Shape-Perception Network from a Single Incomplete Image
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);University of Chinese Academy of Sciences(中国科学院大学);School of Biomedical Engineering, Shenzhen University(深圳大学生物医学工程学院);Gaoling School of Artificial Intelligence, Renmin University of China(中国人民大学高瓴人工智能学院);College of Computer Science and Technology, Qingdao University(青岛大学计算机科学与技术学院)
Three-dimentional reconstruction of complex, dynamic population canopy architecture for crops with a novel point cloud completion model: A case study in Brassica napus rapeseed
A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion
The Chinese University of Hong Kong(香港中文大学);Shanghai AI Laboratory(上海人工智能实验室);Nanyang Technological University(南洋理工大学);University of California, San Diego(加利福尼亚大学圣迭戈分校)
Neural varifolds: an aggregate representation for quantifying the geometry of point clouds
School of Electronics and Computer Science, University of Southampton(南安普顿大学电子与计算机科学学院);Department of Applied Mathematics and Theoretical Physics, University of Cambridge(剑桥大学应用数学与理论物理系);Institut Camille Jordan, Université Claude Bernard Lyon 1(里昂第一大学卡米尔·约旦研究所)
Occlusion-aware Non-Rigid Point Cloud Registration via Unsupervised Neural Deformation Correntropy
Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences(中国科学院香港创新研究院);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学)
SG-GAN: Fine Stereoscopic-Aware Generation for 3D Brain Point Cloud Up-sampling from a Single Image
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);VinUniversity(越南 VinUniversity 大学);College of Engineering and Computer Science(工程与计算机科学学院);School of Software, Tiangong University(天津工业大学软件学院);Department of Mathematics, Hong Kong Baptist University(香港浸会大学数学系)
3D Structural Phenotype of the Optic Nerve Head at the Intersection of Glaucoma and Myopia -- A Key to Improving Glaucoma Diagnosis in Myopic Populations
Singapore Eye Research Institute(新加坡眼科研究所);Singapore National Eye Centre(新加坡国家眼科中心);Singapore-MIT Alliance for Research and Technology(新加坡-麻省理工研究与技术联盟);Duke-NUS Graduate Medical School(杜克-新加坡国立大学医学院);Yong Loo Lin School of Medicine, National University of Singapore(新加坡国立大学杨潞龄医学院);Emory University School of Medicine(埃默里大学医学院);National University of Singapore(新加坡国立大学);Georgia Institute of Technology(佐治亚理工学院);Emory Empathetic AI for Health Institute(埃默里大学共情健康人工智能研究所);Emory Eye Center(埃默里眼科中心);Emory School of Medicine(埃默里医学院);Emory Clinic(埃默里诊所);Abyss Processing Pte Ltd(Abyss Processing私人有限公司)