SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2503.07597 · CVPR · 2025

HumanMM: Global Human Motion Recovery from Multi-shot Videos

Hao Yang, Lei Zhang, Jing Lin, Haoqian Wang, Ling-Hao Chen, Zhuokai Zhao, Yuhong Zhang, Guanlin Wu, Jiamin Wu, Xiaoke Jiang, Zhuoheng Li

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

github.io/HumanMM Figure 1. Recovering a human motion from multi-shot videos. Top: We take two multi-shot table tennis game videos with shot transitions as input. We aim to recover two motions of two athletes (Long MA and Zhendong FAN) from two videos, respectively. The first video is recorded by three shots ("x", "y", and "z" ), and the second one is recovered by two shots ("{" and "|" ). Bottom: We recover two motions (Long MA in green and Zhendong FAN in pink), different shots, and camera poses for each multi-shot video. The recovered motion is aligned with the motion in the videos.

For agents

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

get_harvested_code_for_paper("2503.07597")
get_code_for_paper("2503.07597")
have("2503.07597")

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

curl https://syntology.ai/api/ran/2503.07597.json

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

[![Syntology run record](https://syntology.ai/api/ran/2503.07597.svg)](https://syntology.ai/paper/2503.07597)

Connect an agent — have() is free.