Papers › PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation

PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation

30 Mar 2023CVPR 2023 1arXiv:2303.17472archive 2025-07-28

Qitao Zhao, Ce Zheng, Mengyuan Liu, Pichao Wang, Chen Chen

Recently, transformer-based methods have gained significant success in sequential 2D-to-3D lifting human pose estimation. As a pioneering work, PoseFormer captures spatial relations of human joints in each video frame and human dynamics across frames with cascaded transformer layers and has achieved impressive performance. However, in real scenarios, the performance of PoseFormer and its follow-ups is limited by two factors: (a) The length of the input joint sequence; (b) The quality of 2D joint detection. Existing methods typically apply self-attention to all frames of the input sequence, causing a huge computational burden when the frame number is increased to obtain advanced estimation accuracy, and they are not robust to noise naturally brought by the limited capability of 2D joint detectors. In this paper, we propose PoseFormerV2, which exploits a compact representation of lengthy skeleton sequences in the frequency domain to efficiently scale up the receptive field and boost robustness to noisy 2D joint detection. With minimum modifications to PoseFormer, the proposed method effectively fuses features both in the time domain and frequency domain, enjoying a better speed-accuracy trade-off than its precursor. Extensive experiments on two benchmark datasets (i.e., Human3.6M and MPI-INF-3DHP) demonstrate that the proposed approach significantly outperforms the original PoseFormer and other transformer-based variants. Code is released at \url{https://github.com/QitaoZhao/PoseFormerV2}.

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="2303.17472")

Code

Syntology Ran 5 of 6 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 5 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

qitaozhao/poseformerv2 officialmentioned in papermentioned on GitHubpytorch report
zczcwh/DL-HPE mentioned on GitHub 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

6 samples harvested; 5 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.

5ran
1unverified

Licence: 0 of the 6 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 qitaozhao/poseformerv2. “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.

Attention qitaozhao/poseformerv2/mpi_inf_3dhp/model/model_poseformerv2.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 9af3eb132594e510 · report
Block qitaozhao/poseformerv2/mpi_inf_3dhp/model/model_poseformerv2.py official repository ran · metamorphic tier: deterministic MIT (permissive) · b3bc3259dcec516c · report
FreqMlp qitaozhao/poseformerv2/mpi_inf_3dhp/model/model_poseformerv2.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 872f349e099a1f4c · report
MixedBlock qitaozhao/poseformerv2/mpi_inf_3dhp/model/model_poseformerv2.py official repository ran · metamorphic tier: deterministic MIT (permissive) · d95449711638de93 · report
Mlp qitaozhao/poseformerv2/mpi_inf_3dhp/model/model_poseformerv2.py official repository ran · metamorphic tier: deterministic MIT (permissive) · a1715055832f71fd · report
Model qitaozhao/poseformerv2/mpi_inf_3dhp/model/model_poseformerv2.py official repository unverified MIT (permissive) · abe2a44aafd92702 · report

Tasks

3D Human Pose EstimationClassificationHuman DynamicsPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation MPI-INF-3DHP PoseFormerV2 (T=81) AUC 78.8 #10 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP PoseFormerV2 (T=81) MPJPE 27.8 #10 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP PoseFormerV2 (T=81) PCK 97.9 #10 of 108 Archive leaderboard report
Classification Full-body Parkinson’s disease dataset PoseFormerV2 F1-score (weighted) 0.59 #1 of 7 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