SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.15851 · CVPR · 2022

Neural Inertial Localization

Chen Liu, Yasutaka Furukawa, Yufan Chen, Sachini Herath, David Caruso

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Figure 1. From IMU measurements to location estimates. Given inertial sensor data (left), our approach (center) uses a neural inertial navigation technique to find a sequence of velocity vectors; then train a scene-specific transformer-based neural architecture, which maps a velocity sequence to a location likelihood. The figure shows sample localization results from our office dataset. Color shows temporal correspondence between input(left), intermediate representations(middle), and location (right).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.15851")
get_code_for_paper("2203.15851")
have("2203.15851")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.15851.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.15851.svg)](https://syntology.ai/paper/2203.15851)

Connect an agent — have() is free.