Papers › Humans in 4D: Reconstructing and Tracking Humans with Transformers

Humans in 4D: Reconstructing and Tracking Humans with Transformers

31 May 2023ICCV 2023 1arXiv:2305.20091archive 2025-07-28

Shubham Goel, Georgios Pavlakos, Jathushan Rajasegaran, Angjoo Kanazawa, Jitendra Malik

We present an approach to reconstruct humans and track them over time. At the core of our approach, we propose a fully "transformerized" version of a network for human mesh recovery. This network, HMR 2.0, advances the state of the art and shows the capability to analyze unusual poses that have in the past been difficult to reconstruct from single images. To analyze video, we use 3D reconstructions from HMR 2.0 as input to a tracking system that operates in 3D. This enables us to deal with multiple people and maintain identities through occlusion events. Our complete approach, 4DHumans, achieves state-of-the-art results for tracking people from monocular video. Furthermore, we demonstrate the effectiveness of HMR 2.0 on the downstream task of action recognition, achieving significant improvements over previous pose-based action recognition approaches. Our code and models are available on the project website: https://shubham-goel.github.io/4dhumans/.

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="2305.20091")

Code

Syntology Ran 4 of 5 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 4 ran with no contract checked.

By repository: official repository: 5 samples from 1 repository, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

shubham-goel/4D-Humans officialmentioned on GitHubpytorch 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

5 samples harvested; 4 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.

4ran
1unverified

Licence: 0 of the 5 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 shubham-goel/4D-Humans. “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.

Discriminator shubham-goel/4D-Humans/hmr2/models/hmr2.py official repository ran MIT (permissive) · 044509f32558dfd9 · report
Keypoint2DLoss shubham-goel/4D-Humans/hmr2/models/hmr2.py official repository ran MIT (permissive) · a2086bce04d065c0 · report
Keypoint3DLoss shubham-goel/4D-Humans/hmr2/models/hmr2.py official repository ran MIT (permissive) · b0ad64515a64338e · report
ParameterLoss shubham-goel/4D-Humans/hmr2/models/hmr2.py official repository ran MIT (permissive) · 8afa0da053f74850 · report
HMR2 shubham-goel/4D-Humans/hmr2/models/hmr2.py official repository unverified MIT (permissive) · c3db9cdd4369c570 · report

Tasks

3D Human Pose EstimationAction RecognitionHuman Mesh RecoveryPose Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation 3DPW HMR 2.0 MPJPE 69.8 #23 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW HMR 2.0 MPVPE 82.2 #23 of 119 Archive leaderboard report
3D Human Pose Estimation 3DPW HMR 2.0 PA-MPJPE 44.4 #23 of 119 Archive leaderboard report
Pose Tracking PoseTrack2018 4DHumans + ViTDet IDF1 79.3 #3 of 5 Archive leaderboard report
Pose Tracking PoseTrack2018 4DHumans + ViTDet IDs 367 #3 of 5 Archive leaderboard report
Pose Tracking PoseTrack2018 4DHumans + ViTDet MOTA 61.9 #3 of 5 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.

Methods

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

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