Lune

CVPR2020Top-tier venue

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

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

2020Year
18Top-tier citations

Abstract

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).

Ask about this paper

Your agent reads all of it.

Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.

Questions to start from

Your agent calls

Luneget_paper_fulltext

Ask in Lune

Free to start. No credit card required.

lune papers fulltext 998863c9-9381-4c1c-9a39-e1596949186c

Cited by top-tier papers18

Ask how each one uses it

Builds on2

Related papers

Dusk over the sea between two cliffs drawn in fine vertical lines