TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

Yufu Wang, Ziyun Wang, Lingjie Liu, Kostas Daniilidis
2/14/2026

No official code found. Best implementation: yufu-wang/tram (640 stars, MIT, last commit 2025-06-08). 2 more below.

Abstract

We propose TRAM, a two-stage method to reconstruct a human's global trajectory and motion from in-the-wild videos. TRAM robustifies SLAM to recover the camera motion in the presence of dynamic humans and uses the scene background to derive the motion scale. Using the recovered camera as a metric-scale reference frame, we introduce a video transformer model (VIMO) to regress the kinematic body motion of a human. By composing the two motions, we achieve accurate recovery of 3D humans in the world space, reducing global motion errors by a large margin from prior work. https://yufu-wang.github.io/tram4d/

View on arXivView PDF

Code Implementations(3)

yufu-wang/tramCommunity100%
MIT

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

64063Shell, PythonMar 25, 20241 years agoMIT
upatras-lar/IBRICS_TRAM_forkCommunity68%
MIT

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

10Shell, PythonJun 23, 202510 months agoMIT
bjtulonglong/tramCommunity67%
MIT

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

00Shell, PythonApr 17, 20251 years agoMIT

Similar Papers

Decoupling Human and Camera Motion from Videos in the Wild

91% match2026

WHAM: Reconstructing World-Grounded Humans with Accurate 3D Motion

87% match2026

WATCH: World-aware Allied Trajectory and pose reconstruction for Camera and Human

86% match2025

Motion Diffusion-Guided 3D Global HMR from a Dynamic Camera

86% match2024

Joint Optimization for 4D Human-Scene Reconstruction in the Wild

86% match1 repo2172025

World-Grounded Human Motion Recovery via Gravity-View Coordinates

85% match1 repo2.0k2024

Cite this paper

@article{wang2026tram,
  title  = {TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos},
  author = {Yufu Wang and Ziyun Wang and Lingjie Liu and Kostas Daniilidis},
  year   = {2026},
  eprint = {2403.17346},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2403.17346},
  journal = {ECCV 2024 2024}
}

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/2403.17346.svg)](https://codeofpaper.com/paper/2403.17346)

Discussion