CVMar 26, 2024

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

arXiv:2403.17346v2103 citationsh-index: 22ECCV
Originality Incremental advance
AI Analysis

This addresses the challenge of accurate 3D human motion capture in uncontrolled environments, which is incremental as it builds on existing SLAM and motion estimation methods.

The paper tackles the problem of reconstructing a human's global trajectory and motion from in-the-wild videos, achieving a significant reduction in global motion errors compared to prior work.

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/

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes