![](https://img-blog.csdnimg.cn/20201014180756925.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
human pose estimation
qq_43452156
这个作者很懒,什么都没留下…
展开
-
Consensus-based Optimization for 3D Human Pose Estimation in Camera Coordinates(2019)
Abstract提出一种相机坐标系下的3D估计,可以有效结合2D标注信息和3D姿态,并且有一个多视图融合。将问题分为两个角度:在图像平面以像素级预测3D姿态,以毫米级预测absolute depth。针对未标注图像的多视角预测提出一种基于一致性优化的算法,which requires a single monocular training procedure.Introduction【7,4...原创 2020-03-09 10:50:32 · 484 阅读 · 0 评论 -
Adversarial PoseNet: A Structure-aware Convolutional Network for Human Pose Estimation(2017)
Abstract对于单目图像的Human Pose Estimation,关节遮挡和重叠会导致偏差的姿态预测结果,可能会产生生物学上不可信的姿态预测。相比之下,Human vision通过利用关节连接的几何约束预测姿态。为了解决利用人体结构先验知识这个问题,本文提出a novel structure-aware convolutional network,能够在深度网络的训练过程中...原创 2020-02-20 16:14:03 · 528 阅读 · 0 评论 -
3D Human Pose Estimation = 2D Pose Estimation + Matching(2017)
3D Human Pose Estimation = 2D Pose Estimation + Matching(2017)AbstractMany approaches try to directly predict 3D pose from image measurements,we explore a simple architecture that reasons through in...原创 2020-02-18 21:13:28 · 1153 阅读 · 0 评论 -
3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information(2016)
Keywords: human pose estimation, convolutional neural network, 2D-3D joint optimizationAbstractWe tackle the 3D human pose estimation task with end-to-end learning using CNNs.Relative 3D positions b...原创 2020-02-17 16:41:15 · 537 阅读 · 0 评论 -
3D Human Pose Estimation from Monocular Images with Deep Convolutional Neural Network(2014)
Deep network for 3D pose estimation本文提出两种策略去训练deep convolutional neural network以进行3D pose estimation。网络框架包含两个任务:(1)a joint point regression task;(2)joint point detection tasks。两个任务的输入都是包含human subjec...原创 2020-02-15 21:10:39 · 1372 阅读 · 1 评论 -
Convolutional Pose Machines-base on Pose Machine and Convolutional Network
Abstract**Aim:**使用卷积网络提取图像特征及图像相关空间模型,以进行pose estimationContribution:implicitly model long-range dependencies between variables in structured prediction tasks such as articulated pose estimation m...原创 2019-12-20 14:05:42 · 140 阅读 · 0 评论 -
Pose machines-estimate the 2D pose from a single image
现有关节人体姿态处理都是基于图模型,为了使推理容易,这些方法采用树结构且参数简单。这些模型无法捕捉身体部位之间的交互关系,虽然可以定义更加复杂的模型,但是这些模型的参数学习困难。本文在推理机的基础上,提出一种关节人体姿态估计,融合了多个部位之间丰富的空间关系,既可以在没有专门优化求解器的情况下轻松实现,又可进行有效推理。原创 2019-12-18 21:26:40 · 229 阅读 · 0 评论