Lune

CVPR2020顶会

Optical Non-Line-of-Sight Physics-Based 3D Human Pose Estimation

Mariko Isogawa, Ye Yuan, Matthew O'Toole, Kris M. Kitani

2020年份
18顶会引用

摘要

Hidden person Occluder Imaging system Photon measurements Estimated 3D human poses Wall Frames Figure 1. Non-Line-of-Sight (NLOS) Physics-Based 3D Human Pose Estimation. A pulsed laser and a transient sensor record the time light takes to travel from a point on a wall to the person hidden from sight (left). Given a sequence of 3D transient measurements from an optical NLOS system (top right), our method estimates a 3D pose sequence using a physics-based policy (bottom right).

问问这篇 Paper

智能体会读完全文。

Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。

可以从这些问题问起

智能体调用

Luneget_paper_fulltext

在 Lune 里问

免费开始,无需绑卡

引用它的顶会 Paper18

问问它们各自怎么用它

它引用的顶会 Paper2

相关 Paper

黄昏的海面,两侧是细线勾勒的悬崖