Papers › Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers

Uplift and Upsample: Efficient 3D Human Pose Estimation with Uplifting Transformers

12 Oct 2022arXiv:2210.06110archive 2025-07-28

Moritz Einfalt, Katja Ludwig, Rainer Lienhart

The state-of-the-art for monocular 3D human pose estimation in videos is dominated by the paradigm of 2D-to-3D pose uplifting. While the uplifting methods themselves are rather efficient, the true computational complexity depends on the per-frame 2D pose estimation. In this paper, we present a Transformer-based pose uplifting scheme that can operate on temporally sparse 2D pose sequences but still produce temporally dense 3D pose estimates. We show how masked token modeling can be utilized for temporal upsampling within Transformer blocks. This allows to decouple the sampling rate of input 2D poses and the target frame rate of the video and drastically decreases the total computational complexity. Additionally, we explore the option of pre-training on large motion capture archives, which has been largely neglected so far. We evaluate our method on two popular benchmark datasets: Human3.6M and MPI-INF-3DHP. With an MPJPE of 45.0 mm and 46.9 mm, respectively, our proposed method can compete with the state-of-the-art while reducing inference time by a factor of 12. This enables real-time throughput with variable consumer hardware in stationary and mobile applications. We release our code and models at https://github.com/goldbricklemon/uplift-upsample-3dhpe

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="2210.06110")

Code

Syntology Ran 0 of 17 code samples harvested from 2 repositories linked to this paper; 17 have no recorded run.

By repository: official repository: 9 samples from 1 repository, 0 ran; community (archive-listed): 8 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

goldbricklemon/uplift-upsample-3dhpe officialmentioned in papermentioned on GitHubtfMIT report
kaulquappe23/a2b_human_mesh 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

17 samples harvested; 0 ran; 0 honoured the contract we drafted; 17 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.

17unverified

Licence: 0 of the 17 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

create_image_paths goldbricklemon/uplift-upsample-3dhpe/common/dataset/h36m_splits.py official repository unverified MIT (permissive) · 05ac12c362717f7a · report
drop_path goldbricklemon/uplift-upsample-3dhpe/common/net/vision_transformer.py official repository unverified MIT (permissive) · 6aafcfcb574cb205 · report
image_coordinates goldbricklemon/uplift-upsample-3dhpe/common/dataset/camera.py official repository unverified MIT (permissive) · 7669d6b1ce1e7096 · report
interpolate_between_keyframes goldbricklemon/uplift-upsample-3dhpe/common/dataset/action_wise_eval.py official repository unverified MIT (permissive) · b723e9f4c150f22f · report
mpjpe goldbricklemon/uplift-upsample-3dhpe/common/dataset/metrics.py official repository unverified MIT (permissive) · 3b759fd80717758c · report
nmpjpe goldbricklemon/uplift-upsample-3dhpe/common/dataset/metrics.py official repository unverified MIT (permissive) · 9e168cb44cb7d139 · report
normalize_screen_coordinates goldbricklemon/uplift-upsample-3dhpe/common/dataset/camera.py official repository unverified MIT (permissive) · 82baf6aa4fb040a1 · report
pmpjpe goldbricklemon/uplift-upsample-3dhpe/common/dataset/metrics.py official repository unverified MIT (permissive) · a921292bf596fdc7 · report
tf_mpjpe goldbricklemon/uplift-upsample-3dhpe/common/utils/losses_3d.py official repository unverified MIT (permissive) · eec340f4b62ea073 · report
mpjpe kaulquappe23/a2b_human_mesh/dataset/metrics.py community (archive-listed) unverified MIT (permissive) · 2f8afe6d7dc3c1cc · report
nmpjpe kaulquappe23/a2b_human_mesh/dataset/metrics.py community (archive-listed) unverified MIT (permissive) · ff8248d869523ab9 · report
np_qinverse kaulquappe23/a2b_human_mesh/dataset/quaternion.py community (archive-listed) unverified MIT (permissive) · 3058f77b597a257f · report
np_qrot kaulquappe23/a2b_human_mesh/dataset/quaternion.py community (archive-listed) unverified MIT (permissive) · 8242cae54a825bc8 · report
pmpjpe kaulquappe23/a2b_human_mesh/dataset/metrics.py community (archive-listed) unverified MIT (permissive) · 58f06c045c7a3705 · report
pt_qinverse kaulquappe23/a2b_human_mesh/dataset/uplifiting_dataset.py community (archive-listed) unverified MIT (permissive) · 6a6a59635b7602ec · report
pt_qrot kaulquappe23/a2b_human_mesh/dataset/uplifiting_dataset.py community (archive-listed) unverified MIT (permissive) · 95c89076de9f6be8 · report
world_to_cam_and_2d kaulquappe23/a2b_human_mesh/dataset/uplifiting_dataset.py community (archive-listed) unverified MIT (permissive) · ac0a2e613ce83f5c · report

Tasks

2D Pose Estimation3D Human Pose EstimationMonocular 3D Human Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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