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

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

26 Mar 2024arXiv:2403.17346archive 2025-07-28

Yufu Wang, ZiYun Wang, Lingjie Liu, Kostas Daniilidis

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/

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2403.17346")

Code

Syntology Ran 13 of 14 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 13 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yufu-wang/tram officialpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested; 13 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

13ran
1unverified

Licence: 0 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from yufu-wang/tram. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

cam_wrt_gravity yufu-wang/tram/lib/camera/est_gravity.py official repository ran MIT (permissive) · f97f0472c6ce0b65 · report
cam_wrt_world yufu-wang/tram/lib/camera/est_gravity.py official repository ran MIT (permissive) · 51f1f7730e448854 · report
compute_l2_loss yufu-wang/tram/lib/core/losses.py official repository ran MIT (permissive) · 47e67073b5581024 · report
est_calib yufu-wang/tram/lib/camera/slam_utils.py official repository ran MIT (permissive) · 2dcee438683ee8a4 · report
est_scale_gmof yufu-wang/tram/lib/camera/est_scale.py official repository ran MIT (permissive) · e4c8b52fda09392f · report
est_scale_iterative yufu-wang/tram/lib/camera/est_scale.py official repository ran MIT (permissive) · 43f07fe60d9771d9 · report
get_dimention yufu-wang/tram/lib/camera/slam_utils.py official repository ran MIT (permissive) · 3d45d8fea0a6ba6f · report
get_lr_cycle_scheduler yufu-wang/tram/lib/core/base_trainer.py official repository ran MIT (permissive) · 9b09946e117bbab5 · report
get_lr_scheduler yufu-wang/tram/lib/core/base_trainer.py official repository ran MIT (permissive) · 9b438214a4dff91b · report
keypoint_loss yufu-wang/tram/lib/core/losses.py official repository ran MIT (permissive) · ddd90785d243b136 · report
parse_args yufu-wang/tram/lib/core/config.py official repository ran MIT (permissive) · 8a1791646b3bf7ea · report
preprocess_masks yufu-wang/tram/lib/camera/slam_utils.py official repository ran MIT (permissive) · 87f90af29b982adb · report
update_cfg yufu-wang/tram/lib/core/config.py official repository ran MIT (permissive) · 8cae4a5d48fbd269 · report
keypoint_3d_loss yufu-wang/tram/lib/core/losses.py official repository unverified MIT (permissive) · df63348c72c98591 · report

Tasks

3D Human Pose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation EMDB TRAM Average MPJPE (mm) 74.4 #1 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB TRAM Average MPJPE-PA (mm) 45.7 #1 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB TRAM Average MVE (mm) 86.6 #1 of 13 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections