CoMotion: Concurrent Multi-person 3D Motion

Alejandro Newell, Peiyun Hu, Lahav Lipson, Stephan R. Richter, Vladlen Koltun
4/16/2025
cs.CVcs.LG

Official code: apple/ml-comotion (302 stars, last commit 2025-04-16).

Abstract

We introduce an approach for detecting and tracking detailed 3D poses of multiple people from a single monocular camera stream. Our system maintains temporally coherent predictions in crowded scenes filled with difficult poses and occlusions. Our model performs both strong per-frame detection and a learned pose update to track people from frame to frame. Rather than match detections across time, poses are updated directly from a new input image, which enables online tracking through occlusion. We train on numerous image and video datasets leveraging pseudo-labeled annotations to produce a model that matches state-of-the-art systems in 3D pose estimation accuracy while being faster and more accurate in tracking multiple people through time. Code and weights are provided at https://github.com/apple/ml-comotion

View on arXivView PDF

Code Implementations(1)

apple/ml-comotionOfficial100%
30226Shell, PythonApr 15, 20251 years agoNOASSERTION

Similar Papers

End-to-End Multi-Person Pose Estimation with Pose-Aware Video Transformer

84% match1 repo252025

CasCalib: Cascaded Calibration for Motion Capture from Sparse Unsynchronized Cameras

83% match1 repo102024

Proactive Multi-Camera Collaboration For 3D Human Pose Estimation

83% match1 repo482023

Reconstructing Close Human Interactions from Multiple Views

83% match1 repo402024

Snipper: A Spatiotemporal Transformer for Simultaneous Multi-Person 3D Pose Estimation Tracking and Forecasting on a Video Snippet

83% match1 repo362022

Motions as Queries: One-Stage Multi-Person Holistic Human Motion Capture

82% match1 repo102025

Cite this paper

@article{newell2025comotion,
  title  = {CoMotion: Concurrent Multi-person 3D Motion},
  author = {Alejandro Newell and Peiyun Hu and Lahav Lipson and Stephan R. Richter and Vladlen Koltun},
  year   = {2025},
  eprint = {2504.12186},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2504.12186v1},
  journal = {ICLR 2025 2025}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2504.12186.svg)](https://codeofpaper.com/paper/2504.12186)

Discussion