Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Vision-to-Motion on Human3.6M benchmark leaderboard · SOTA2 Research

Research Benchmarks

Vision-to-Motion on Human3.6M

75MPJPEUniMotion

Updated 4mo ago

Evaluation Results

Method	Links
UniMotion2026.03		75
UniPose2026.03		81.8

SOTA Paper

UniMotion

UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation

Dataset

Human3.6M

Follow for updates

Join SOTA2 Contact

Related Benchmarks

Motion-to-Text on HumanML3D Vision-to-Motion on Human3.6M (test)Text-conditioned motion editing on MotionFix Vision-to-Text on H3.6M Motion Prediction on AMASS HumanML3D