Taylor3DNet: Fast 3D Shape Inference With Landmark Points Based Taylor Series
ShanghaiTech University（上海科技大学）；Shanghai Engineering Research Center of Intelligent Vision and Imaging（上海智能视觉与成像工程研究中心）；Shanghai Engineering Research Center of Energy Efficient and Custom AI IC（上海高效节能定制人工智能芯片工程研究中心）
本文提出 Taylor3DNet，利用离散地标点及其 Taylor 级数系数表示三维隐式场，将查询点评估简化为低阶 Taylor 计算，从而在多种重建任务中显著加速且不降低精度。
摘要：
得益于连续表示能力，深度隐式函数能够以无限分辨率表示形状。然而，从隐式函数中提取高分辨率等值面需要对大量查询点前向传播一个参数量庞大的网络，从而限制了生成速度。受 Taylor 级数启发，我们提出 Taylor3DNet 以加速隐式形状表示的推理。Taylor3DNet 利用一组离散地标点及其对应的 Taylor 级数系数来表示三维形状的隐式场，且地标点数量与等值面提取的分辨率无关。一旦预测出与地标点对应的系数，对每个查询点的网络评估便可简化为利用若干最近地标点进行的低阶 Taylor 级数计算。基于这一高效表示，我们的 Taylor3DNet 相比经典的基于网络的隐式函数实现了显著更快的推理速度。我们在具有多种输入类型的重建任务上评估了该方法，结果表明，与最先进基线相比，我们的方法能够在不牺牲性能的情况下大幅提升推理速度。
英文摘要：
Benefiting from the continuous representation ability, deep implicit functions can represent a shape at infinite resolution. However, extracting high-resolution iso-surface from an implicit function requires forward-propagating a network with a large number of parameters for numerous query points, thus preventing the generation speed. Inspired by the Taylor series, we propose Taylo3DNet to accelerate the inference of implicit shape representations. Taylor3DNet exploits a set of discrete landmark points and their corresponding Taylor series coefficients to represent the implicit field of a 3D shape, and the number of landmark points is independent of the resolution of the iso-surface extraction. Once the coefficients corresponding to the landmark points are predicted, the network evaluation for each query point can be simplified as a low-order Taylor series calculation with several nearest landmark points. Based on this efficient representation, our Taylor3DNet achieves a significantly faster inference speed than classical network-based implicit functions. We evaluate our approach on reconstruction tasks with various input types, and the results demonstrate that our approach can improve the inference speed by a large margin without sacrificing the performance compared with state-of-the-art baselines.
Fast Landmark Localization with 3D Component Reconstruction and CNN for Cross-Pose Recognition
National Taiwan University of Science and Technology（台湾科技大学）
提出了两种用于交叉姿态人脸识别的方法，一种是基于面部部件的3D重建，另一种是基于深度卷积神经网络（CNN）。与大多数考虑整体面部的3D方法不同，所提出的方法考虑3D面部组件。它将2D图库面分割为元件，为每个元件重建3D曲面，并通过元件特征识别探测面。分割基于分层算法定位的地标，该算法结合了用于人脸检测的Faster R-CNN和用于地标定位的Reduced Tree Structured Model。基于CNN的方法的核心部分是修改的VGG网络。我们研究了训练集上不同设置的性能，包括来自3D重建的合成数据，来自野外数据库的真实数据，以及两种类型的数据组合。我们调查的网络时，它被用作分类器或设计为一个特征提取器的性能。这两种识别方法和快速地标定位进行了评估，在广泛的实验，并比较国家的最先进的方法，以证明其有效性。
Fast and Robust Localization for Humanoid Soccer Robot via Iterative Landmark Matching
Robotics and Mechanisms Laboratory (RoMeLa), Department of Mechanical and Aerospace Engineering, University of California, Los Angeles（机器人与机制实验室（RoMeLa）、机械与航空航天工程系、加州大学洛杉矶分校）
TaylorGrid: Towards Fast and High-Quality Implicit Field Learning via Direct Taylor-based Grid Optimization
School of Artificial Intelligence, Jilin University（吉林大学人工智能学院）；School of Computer Science and Engineering, Nanyang Technological University（南洋理工大学计算机科学与工程学院）
Spinal ligaments detection on vertebrae meshes using registration and 3D edge detection
University of Koblenz（科布伦茨大学）；Institute for Computational Visualistics（计算视觉研究所）；Intelligent Autonomous Systems Group（智能自主系统组）；Institute for Medical Technology and Information Processing（医学技术与信息处理研究所）
Real-time landmark detection for precise endoscopic submucosal dissection via shape-aware relation network
Xiamen University（厦门大学）；The Chinese University of Hong Kong（香港中文大学）；Zhongshan Hospital affiliated to Xiamen University（厦门大学附属中山医院）；The Hong Kong Polytechnic University（香港理工大学）
Submillimeter-Accurate 3D Lumbar Spine Reconstruction from Biplanar X-Ray Images: Incorporating a Multi-Task Network and Landmark-Weighted Loss
School of Biomedical Engineering & Med-X Research Institute, Shanghai Jiao Tong University（上海交通大学生物医学工程学院与Med-X研究院）；Engineering Research Center of Digital Medicine and Clinical Translation, Ministry of Education（教育部数字医学临床转化工程研究中心）；Department of Spine Surgery, Tongji Hospital, School of Medicine, Tongji University（同济大学医学院附属同济医院脊柱外科）；TAOiMAGE Medical Technologies Corporation（TAOiMAGE医疗科技有限公司）；School of Mechanical Engineering, Shanghai Jiao Tong University（上海交通大学机械工程学院）
