Papers › 3D Human Pose Estimation with Spatial and Temporal Transformers

3D Human Pose Estimation with Spatial and Temporal Transformers

18 Mar 2021ICCV 2021 10arXiv:2103.10455archive 2025-07-28

Ce Zheng, Sijie Zhu, Matias Mendieta, Taojiannan Yang, Chen Chen, Zhengming Ding

Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation. However, in the field of human pose estimation, convolutional architectures still remain dominant. In this work, we present PoseFormer, a purely transformer-based approach for 3D human pose estimation in videos without convolutional architectures involved. Inspired by recent developments in vision transformers, we design a spatial-temporal transformer structure to comprehensively model the human joint relations within each frame as well as the temporal correlations across frames, then output an accurate 3D human pose of the center frame. We quantitatively and qualitatively evaluate our method on two popular and standard benchmark datasets: Human3.6M and MPI-INF-3DHP. Extensive experiments show that PoseFormer achieves state-of-the-art performance on both datasets. Code is available at https://github.com/zczcwh/PoseFormer

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 8 code samples harvested from 2 repositories linked to this paper: 4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 2 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 6 samples from 1 repository, 2 ran (2 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

zczcwh/PoseFormer officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
thuxyz19/test mentioned on GitHubpytorchSyntology: 6 samples, 2 ran (0 instrument-failed) · 4 unverified report
zczcwh/DL-HPE mentioned on GitHubSyntology: not harvested 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

8 samples harvested: 4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran
4unverified

Licence: 8 of the 8 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

zczcwh/PoseFormer official repository 2 samples, 2 ran (0 instrument-failed) · 0 unverified
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
common/model_poseformer.py ran no licence file found · pointer only · 806376d9202b2bc9 · report fixture: returned Block · level recorded 2026-09-22
PoseTransformer common/model_poseformer.py ran no licence file found · pointer only · d33650ab39737101 · report fixture: returned PoseTransformer · level recorded 2026-09-22
thuxyz19/test community (archive-listed) 6 samples, 2 ran (0 instrument-failed) · 4 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
common/model_poseformer.py ran · metamorphic tier: invariant no licence file found · pointer only · fab27d0fb962f729 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
DownSampleAttention common/model_poseformer.py ran no licence file found · pointer only · 566d7093b72572b4 · report fixture: signature x:Tensor/3/float · returned tuple · level recorded 2026-09-24
PoseTransformer common/model_poseformer.py unverified no licence file found · pointer only · 09d4b28562865d41 · report
ProbSparseAttention common/model_poseformer.py unverified no licence file found · pointer only · 5a96e44e698f69e0 · report
TBlock common/model_poseformer.py unverified no licence file found · pointer only · 3c604929660e9363 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for PoseFormer (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for PoseFormer (graph method: PoseFormer). 4 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. PoseTransformer entry · level 1 · ran · d33650ab39737101
  2. Block model · level 1 · ran · 806376d9202b2bc9
  3. Attention model · level 1 · ran · 9af3eb132594e510
  4. Mlp model · level 1 · ran · a1715055832f71fd

harvested Assembly for PoseFormer (graph method: PoseFormer). 7 bricks; individually on a fixture: 3 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. PoseTransformer entry · level 0 · unverified · 09d4b28562865d41
  2. Attention model · level 1 · ran · fab27d0fb962f729
  3. Block model · level 0 · unverified · 4b147c20666e9018
  4. DownSampleAttention helper · level 1 · ran · 566d7093b72572b4
  5. ProbSparseAttention helper · level 0 · unverified · 5a96e44e698f69e0
  6. TBlock model · level 0 · unverified · 3c604929660e9363
  7. Mlp helper · level 1 · ran · a1715055832f71fd

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2103.10455") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Human Pose EstimationImage ClassificationMonocular 3D Human Pose EstimationObject DetectionPose EstimationSemantic Segmentationimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M PoseFormer (f=81) Average MPJPE (mm) 44.3 #35 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M PoseFormer (f=81) Multi-View or Monocular Monocular #35 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M PoseFormer (f=81) Using 2D ground-truth joints No #35 of 88 Archive leaderboard report
3D Human Pose Estimation HumanEva-I PoseFormer Mean Reconstruction Error (mm) 21.6 #13 of 31 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP PoseFormer (9 frames) AUC 56.4 #36 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP PoseFormer (9 frames) MPJPE 77.1 #36 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP PoseFormer (9 frames) PCK 88.6 #36 of 108 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M PoseFormer (T=81) 2D detector CPN #15 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M PoseFormer (T=81) Average MPJPE (mm) 44.3 #15 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M PoseFormer (T=81) Frames Needed 81 #15 of 52 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