ElasticFusion 是　kinnectfusion 的升级版，3D建模的必读文章

通过3D密集人脸重建实现稳定的头部姿势估计和地标回归 通过Tensorflow Lite框架，人脸网格，头部姿势，界标等，重新实现。 CPU实时人脸检测，对齐和重建管线。 轻量级渲染库，比工具快5倍（3对 。 通过单个网络的相机矩阵和密集/稀疏地标预测。 生成面部参数以实现可靠的头部姿势和表情估计。 设置 基本要求 Python 3.6+ pip3 install -r requirements.txt 渲染致密脸 GCC 6.0+ bash build_render.sh （谨慎）对于Windows用户，请参考以获取更多详细信息。 3D人脸地标 在这个项目中，我们通过3DMM参数回归进行密集人脸重建。 回归目标简化为相机矩阵（ C ，形状为3x4），外观参数（ S ，形状为1x40）和表达变量（ E ，形状为1x10），共有62个维度。 可以通过将这些参数应用于预定义的

双目密集立体 使用双目立体的多视图重建

opencv_dense_flow依赖文件.zip

Ultra-Dense Networks for 5G and Beyond：Modelling, Analysis, and Applications Ultra-Dense Networks for 5G and Beyond：Modelling, Analysis, and App.pdf (8.28 MB, 下载次数: 137 ) We are observing an ever-increasing number of connected devices and the rapid growth of bandwidth-intensive wireless applications. Te number of wirelessly connected devices is anticipated to exceed 11.5 billion by 2019, i.e. nearly 1.5 mobile devices per capita. In addition, it is expected that we will witness a 10 000-fold growth in wireless data traffic by the year 2030. Such unprecedented increases in mobile data traffic and network loads are pushing contemporary wireless network infrastructures to a breaking point. Tese predictions have raised alarm to the wireless industry and mobile network operators who are faced with the challenges of provisioning high-rate, low-delay, and highly reliable connectivity anytime and anywhere without ignificantly increasing energy consumption at the infrastructure, such as base stations, fronthaul and backhaul networks, and core networks.

此文件是稠密尺度不变特征提取（dense Sift），用于图像特征提取 , 大家注意是matlab版本的

原文是：Joint 3D Face Reconstruction and Dense Face Alignm 在看论文的时候顺便把中文翻译搞出来，方便需要的朋友。

2020CVPR顶会图像去雾论文-Multi-Scale Boosted Dehazing Network with Dense Feature Fusion论文源码

Dense_RGB-D_SLAM_with_multiple_cameras[1].pdf

hive中分组取topN、row_number、rank和dense_rank使用介绍