SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2103.06182 · ICCV · 2021

Dynamical Pose Estimation

Mit, Jean-Jacques Slotine, Yang Heng

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

Virtual Springs Camera Frame Category Model 2D Keypoints Bearing Vectors (a) Point Cloud Registration (b) Primitive Registration (c) Category Registration (d) Absolute Pose Estimation (e) Category APE Figure 1: We propose DynAMical Pose estimation (DAMP), the first general and practical framework to perform pose estimation from 2D and 3D visual correspondences by simulating rigid body dynamics arising from virtual springs and damping (top row, magenta lines). DAMP almost always returns the globally optimal rigid transformation across five pose estimation problems (bottom row). (a) Point cloud registration using the Bunny dataset [16]; (b) Primitive registration using a robot model of spheres, planes, cylinders and cones; (c) Category registration using the chair category from the PASCAL3D+ dataset [51]; (d) Absolute pose estimation (APE) using the SPEED satellite dataset [45]; (e) Category APE using the FG3DCar dataset [34].

For agents

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

get_harvested_code_for_paper("2103.06182")
get_code_for_paper("2103.06182")
have("2103.06182")

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

curl https://syntology.ai/api/ran/2103.06182.json

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

[![Syntology run record](https://syntology.ai/api/ran/2103.06182.svg)](https://syntology.ai/paper/2103.06182)

Connect an agent — have() is free.