Skip to content
RobotWorld
← Back to Videos

UMR: Unified Motion Retargeting via Learned Point Cloud Correspondence

Loading video
Loading video

UMR learns dense point cloud correspondences as a unified interface for transferring human motion across heterogeneous humanoid embodiments, replacing hand-crafted keypoint mappings with constrained point cloud matching that aligns surface poses and transfers interaction contacts.

HumanoidMotion retargetingPoint Cloud CorrespondenceLocomotionContact-Rich ManipulationOpen Source
Category: humanoid
Author: @Runyi_Ingrid_Yu
Date: 2026-09-11T00:00:00
Duration: 123.297s
Source: https://x.com/Runyi_Ingrid_Yu/status/2098394175494586725
Reference: https://hanyang9.github.io/UMR/

Related Videos

HumanoidPose Estimates Full-Body Humanoid Pose from Video
1:17

HumanoidPose Estimates Full-Body Humanoid Pose from Video

@cs_jiaxi_jiang · 91 views · 2026-10-22
HumanoidPose estimation
ORCS Releases a Humanoid Whole-Body Controller Toolkit
0:14

ORCS Releases a Humanoid Whole-Body Controller Toolkit

@lok_s_h · 1.1k views · 2026-09-14
HumanoidWhole-Body Control
A Humanoid That Chooses Contact Points to Cross Terrain
1:13

A Humanoid That Chooses Contact Points to Cross Terrain

@ZappyZappy7 · 67 views · 2026-10-25
HumanoidLocomotion
MicroBan: A $600 Open-Source 3D-Printed Humanoid
1:46

MicroBan: A $600 Open-Source 3D-Printed Humanoid

@techniahqrobot · 114 views · 2026-10-15
HumanoidOpen Source
TERRA: Reconstructing Terrains from Motion Data for Muscle-Actuated Control
3:00

TERRA: Reconstructing Terrains from Motion Data for Muscle-Actuated Control

@tokufxug · 127 views · 2026-10-18
Musculoskeletal ModelMotion retargeting
PLEN2: A Printable Open-Source Humanoid, Design and Code Fully on GitHub
1:23

PLEN2: A Printable Open-Source Humanoid, Design and Code Fully on GitHub

@techniahqrobot · 145 views · 2026-10-17
PLEN2Humanoid

As an Amazon Associate, we earn from qualifying purchases.