Pith. sign in

REVIEW 5 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.17346 v2 pith:OEQYZXND submitted 2024-03-26 cs.CV

Yufu Wang , Ziyun Wang , Lingjie Liu , Kostas Daniilidis This is my paper · ORCID
classification cs.CV
keywords motionglobalhumanstramcamerahumanin-the-wildtrajectory
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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/

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Sen-Cap: Sensor-Flexible and Noise-Resilient Human Motion Capture via LiDAR-Camera Integration

    cs.CV 2026-08 conditional novelty 6.0 of 10

    Sen-Cap estimates 3D human pose and global trajectory from flexible, uncalibrated combinations of LiDARs and cameras, setting state-of-the-art scores on Human-M3 and FreeMotion while tolerating point-cloud noise.

  2. EgoHTR: Egocentric 4D Demonstrations of Human Terrain Traversal

    cs.RO 2026-07 conditional novelty 6.0 of 10

    EgoHTR is a 55-sequence, 150k-frame egocentric 4D human-terrain dataset with a reconstruction pipeline, MoCap-validated benchmark, and perceptive locomotion policies deployed on a Unitree G1.

  3. Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset

    cs.CV 2025-01 conditional novelty 6.0 of 10

    Motion-X++ provides 19.5M 3D whole-body pose annotations across 120.5K sequences with text, audio, video, and motion modalities.

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

    cs.CV 2025-01 conditional novelty 6.0 of 10

    By jointly optimizing human motion, camera poses, and dense scene geometry with human-scene contact constraints, JOSH attains state-of-the-art global human motion and scene reconstruction from monocular web videos.

  5. Reconstructing People, Places, and Cameras

    cs.CV 2024-12 conditional novelty 6.0 of 10

    HSfM jointly optimizes human meshes, dense scene pointmaps, and camera poses in a metric world frame, reducing world-frame human joint error from 3.5m to 1.0m on EgoHumans.

Pith tools