Papers › WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion

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

12 Dec 2023CVPR 2024 1arXiv:2312.07531archive 2025-07-28

Soyong Shin, Juyong Kim, Eni Halilaj, Michael J. Black

The estimation of 3D human motion from video has progressed rapidly but current methods still have several key limitations. First, most methods estimate the human in camera coordinates. Second, prior work on estimating humans in global coordinates often assumes a flat ground plane and produces foot sliding. Third, the most accurate methods rely on computationally expensive optimization pipelines, limiting their use to offline applications. Finally, existing video-based methods are surprisingly less accurate than single-frame methods. We address these limitations with WHAM (World-grounded Humans with Accurate Motion), which accurately and efficiently reconstructs 3D human motion in a global coordinate system from video. WHAM learns to lift 2D keypoint sequences to 3D using motion capture data and fuses this with video features, integrating motion context and visual information. WHAM exploits camera angular velocity estimated from a SLAM method together with human motion to estimate the body's global trajectory. We combine this with a contact-aware trajectory refinement method that lets WHAM capture human motion in diverse conditions, such as climbing stairs. WHAM outperforms all existing 3D human motion recovery methods across multiple in-the-wild benchmarks. Code will be available for research purposes at http://wham.is.tue.mpg.de/

PaperPDFConference PDFCodeCode 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="2312.07531")

Code

Syntology Ran 3 of 12 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 3 ran with no contract checked.

By repository: community (archive-listed): 12 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yohanshin/WHAM mentioned on GitHubpytorchMIT 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

12 samples harvested; 3 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran
9unverified

Licence: 0 of the 12 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 yohanshin/WHAM. “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.

compute_accel yohanshin/WHAM/lib/eval/eval_utils.py community (archive-listed) ran MIT (permissive) · 58d59e9d2a8a0240 · report
compute_error_accel yohanshin/WHAM/lib/eval/eval_utils.py community (archive-listed) ran MIT (permissive) · 35c6e596e9bc4bb2 · report
compute_error_verts yohanshin/WHAM/lib/eval/eval_utils.py community (archive-listed) ran MIT (permissive) · 8e5bf3cf235ab46d · report
bool_arg yohanshin/WHAM/configs/config.py community (archive-listed) unverified MIT (permissive) · fe7aa89a39f9cc8b · report
contact_loss yohanshin/WHAM/lib/core/loss.py community (archive-listed) unverified MIT (permissive) · e4d2ae7f674acab9 · report
extract_cam_param_xml yohanshin/WHAM/lib/data_utils/rich_eval_utils.py community (archive-listed) unverified MIT (permissive) · 869298cb3b9cfb7e · report
full_projected_keypoint_loss yohanshin/WHAM/lib/core/loss.py community (archive-listed) unverified MIT (permissive) · cea0af0de65ed3e1 · report
get_cfg yohanshin/WHAM/configs/config.py community (archive-listed) unverified MIT (permissive) · 2039dbb6edef87be · report
is_dset yohanshin/WHAM/lib/data_utils/emdb_eval_utils.py community (archive-listed) unverified MIT (permissive) · d47bdae1805ba57f · report
load_video yohanshin/WHAM/wham_api.py community (archive-listed) unverified MIT (permissive) · f5e1eddc0f7791f2 · report
parse_args yohanshin/WHAM/configs/config.py community (archive-listed) unverified MIT (permissive) · 92381a84384aef12 · report
root_loss yohanshin/WHAM/lib/core/loss.py community (archive-listed) unverified MIT (permissive) · 50063b39bbec654b · report

Tasks

3D Human Pose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation 3DPW WHAM (ViT) MPJPE 57.8 #2 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW WHAM (ViT) MPVPE 68.7 #2 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW WHAM (ViT) PA-MPJPE 35.9 #2 of 119 Archive leaderboard report
3D Human Pose Estimation EMDB WHAM (ViT) Average MPJPE (mm) 79.7 #2 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB WHAM (ViT) Average MPJPE-PA (mm) 50.4 #2 of 13 Archive leaderboard report
3D Human Pose Estimation EMDB WHAM (ViT) Average MVE (mm) 94.4 #2 of 13 Archive leaderboard report
3D Human Pose Estimation RICH WHAM (ViT) MPJPE 80 #4 of 4 Archive leaderboard report
3D Human Pose Estimation RICH WHAM (ViT) MPVPE 91.2 #4 of 4 Archive leaderboard report
3D Human Pose Estimation RICH WHAM (ViT) PA-MPJPE 44.3 #4 of 4 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