Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation

Ye Yuan, Kris Kitani, Zhengyi Luo, Ryo Hachiuma

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repository	Role	Ran
KlabCMU/kin-poly	—	0 of 2

Function	Status	Where it lives
Flags	Not yet run	KlabCMU/kin-poly/kin_poly/core/reward_function.py code served (permissive licence) · get_code("d51ef39164f8e5e7")
dynamic_supervision_v1	Not yet run	KlabCMU/kin-poly/kin_poly/core/reward_function.py code served (permissive licence) · get_code("b8db6df2a1e987fe")

Repositories linked to this paper

KlabCMU/kin-poly — marked official in Papers with Code

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

Abstract

Figure 1: From egocentric videos, we infer physically-plausible 3D human pose and human-object interaction.

For agents

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

get_harvested_code_for_paper("2106.05969")
get_code_for_paper("2106.05969")
have("2106.05969")

Connect an agent — have() is free.