Papers › KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human...

KTPFormer: Kinematics and Trajectory Prior Knowledge-Enhanced Transformer for 3D Human Pose Estimation

31 Mar 2024CVPR 2024 1arXiv:2404.00658archive 2025-07-28

Jihua Peng, Yanghong Zhou, P. Y. Mok

This paper presents a novel Kinematics and Trajectory Prior Knowledge-Enhanced Transformer (KTPFormer), which overcomes the weakness in existing transformer-based methods for 3D human pose estimation that the derivation of Q, K, V vectors in their self-attention mechanisms are all based on simple linear mapping. We propose two prior attention modules, namely Kinematics Prior Attention (KPA) and Trajectory Prior Attention (TPA) to take advantage of the known anatomical structure of the human body and motion trajectory information, to facilitate effective learning of global dependencies and features in the multi-head self-attention. KPA models kinematic relationships in the human body by constructing a topology of kinematics, while TPA builds a trajectory topology to learn the information of joint motion trajectory across frames. Yielding Q, K, V vectors with prior knowledge, the two modules enable KTPFormer to model both spatial and temporal correlations simultaneously. Extensive experiments on three benchmarks (Human3.6M, MPI-INF-3DHP and HumanEva) show that KTPFormer achieves superior performance in comparison to state-of-the-art methods. More importantly, our KPA and TPA modules have lightweight plug-and-play designs and can be integrated into various transformer-based networks (i.e., diffusion-based) to improve the performance with only a very small increase in the computational overhead. The code is available at: https://github.com/JihuaPeng/KTPFormer.

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="2404.00658")

Code

Syntology Ran 6 of 10 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · our draft was wrong; 4 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

JihuaPeng/KTPFormer officialmentioned in paperpytorch 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

10 samples harvested; 6 ran; 0 honoured the contract we drafted; 4 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.

1ran · violated contract
1ran · our draft was wrong
4ran
4unverified

Licence: 10 of the 10 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 JihuaPeng/KTPFormer. “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.

mpjpe JihuaPeng/KTPFormer/common/loss.py official repository ran no licence file found · pointer only · 8e11f61858f90f83 · report
normalize JihuaPeng/KTPFormer/common/graph_utils.py official repository ran · violated contract no licence file found · pointer only · aa9c29936dee40a7 · report
p_mpjpe JihuaPeng/KTPFormer/common/loss.py official repository ran no licence file found · pointer only · 29d56deadc8fcd3c · report
qinverse JihuaPeng/KTPFormer/common/quaternion.py official repository ran fingerprinted no licence file found · pointer only · 6cc69ac50608b9b0 · report
qrot JihuaPeng/KTPFormer/common/quaternion.py official repository ran no licence file found · pointer only · 34067eef72357f72 · report
sparse_mx_to_torch_sparse_tensor JihuaPeng/KTPFormer/common/graph_utils.py official repository ran · our draft was wrong no licence file found · pointer only · bdc1f1dad6d978e7 · report
adj_mx_from_edges JihuaPeng/KTPFormer/common/graph_utils.py official repository unverified no licence file found · pointer only · 8080a0e016046baf · report
image_coordinates JihuaPeng/KTPFormer/common/camera.py official repository unverified no licence file found · pointer only · 7669d6b1ce1e7096 · report
normalize_screen_coordinates JihuaPeng/KTPFormer/common/camera.py official repository unverified no licence file found · pointer only · 82baf6aa4fb040a1 · report
weighted_mpjpe JihuaPeng/KTPFormer/common/loss.py official repository unverified no licence file found · pointer only · 09a4e544aff13453 · report

Tasks

3D Human Pose EstimationMonocular 3D Human Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Human Pose Estimation Human3.6M KTPFormer (T=243) Average MPJPE (mm) 33.0 #12 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M KTPFormer (T=243) Multi-View or Monocular Monocular #12 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M KTPFormer (T=243) PA-MPJPE 26.2 #12 of 88 Archive leaderboard report
3D Human Pose Estimation Human3.6M KTPFormer (T=243) Using 2D ground-truth joints No #12 of 88 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP KTPFormer AUC 85.9 #3 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP KTPFormer MPJPE 16.7 #3 of 108 Archive leaderboard report
3D Human Pose Estimation MPI-INF-3DHP KTPFormer PCK 98.9 #3 of 108 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M KTPFormer 2D detector CPN #10 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M KTPFormer Average MPJPE (mm) 40.1 #10 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M KTPFormer Frames Needed 243 #10 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M KTPFormer Need Ground Truth 2D Pose No #10 of 52 Archive leaderboard report
Monocular 3D Human Pose Estimation Human3.6M KTPFormer Use Video Sequence Yes #10 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.

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