Implicit neural networks have been successfully used for surface reconstruction from point clouds. However, many of them face scalability issues as they encode the isosurface function of a whole object or scene into a single latent vector. To overcome this limitation, a few approaches infer latent vectors on a coarse regular 3D grid or on 3D patches, and interpolate them to answer occupancy queries. In doing so, they loose the direct connection with the input points sampled on the surface of objects, and they attach information uniformly in space rather than where it matters the most, i.e., near the surface. Besides, relying on fixed patch sizes may require discretization tuning. To address these issues, we propose to use point cloud convolutions and compute latent vectors at each input point. We then perform a learning-based interpolation on nearest neighbors using inferred weights. Experiments on both object and scene datasets show that our approach significantly outperforms other methods on most classical metrics, producing finer details and better reconstructing thinner volumes. The code is available at https://github.com/valeoai/POCO.
A Point Cloud Generative Model via Tree-Structured Graph Convolutions for 3D Brain Shape Reconstruction
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);Shenzhen University(深圳大学);Renmin University of China(中国人民大学)
ETH Zurich(苏黎世联邦理工学院);Max Planck Institute for Intelligent Systems, Tübingen(马克斯·普朗克智能系统研究所(蒂宾根));University of Tübingen(蒂宾根大学);Amazon, Tübingen(亚马逊(蒂宾根));Microsoft(微软)
SRSNetwork: Siamese Reconstruction-Segmentation Networks based on Dynamic-Parameter Convolution
School of Automation and Intelligent Sensing & Institute of Image Processing and Pattern Recognition & Institute of Medical Robotics, Shanghai Jiao Tong University(自动化与智能感知学院及图像处理与模式识别研究所及医学机器人研究所,上海交通大学);School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China(生物医学工程学院,生命科学与医学系,中国科学技术大学);Suzhou Institute for Advanced Research, University of Science and Technology of China(中国科学技术大学苏州市先进研究院);School of Computer Science and Technology, Zhejiang Normal University(计算机科学与技术学院,浙江师范大学);Harbin Institute of Technology(哈尔滨工业大学)
Dual-Octave Convolution for Accelerated Parallel MR Image Reconstruction
Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));Peng Cheng Laboratory(鹏城实验室);University of Electronic Science and Technology of China(电子科技大学);Inception Institute of Artificial Intelligence(人工智能起源研究所)
Fast Fourier Convolutional GAN for 30 m Clear-Sky Land Surface Temperature Gap-Free Reconstruction
Technical University of Munich(慕尼黑工业大学);Helmholtz Centre for Polar and Marine Research, Alfred Wegener Institute(亥姆霍兹极地与海洋研究中心阿尔弗雷德·韦格纳研究所);Swiss Federal Institute of Technology Zurich (ETH Zurich)(瑞士联邦理工学院苏黎世分校)