Papers › A Simple Baseline for Efficient Hand Mesh Reconstruction

A Simple Baseline for Efficient Hand Mesh Reconstruction

4 Mar 2024CVPR 2024 1arXiv:2403.01813archive 2025-07-28

Zhishan Zhou, Shihao. zhou, Zhi Lv, Minqiang Zou, Yao Tang, Jiajun Liang

3D hand pose estimation has found broad application in areas such as gesture recognition and human-machine interaction tasks. As performance improves, the complexity of the systems also increases, which can limit the comparative analysis and practical implementation of these methods. In this paper, we propose a simple yet effective baseline that not only surpasses state-of-the-art (SOTA) methods but also demonstrates computational efficiency. To establish this baseline, we abstract existing work into two components: a token generator and a mesh regressor, and then examine their core structures. A core structure, in this context, is one that fulfills intrinsic functions, brings about significant improvements, and achieves excellent performance without unnecessary complexities. Our proposed approach is decoupled from any modifications to the backbone, making it adaptable to any modern models. Our method outperforms existing solutions, achieving state-of-the-art (SOTA) results across multiple datasets. On the FreiHAND dataset, our approach produced a PA-MPJPE of 5.7mm and a PA-MPVPE of 6.0mm. Similarly, on the Dexycb dataset, we observed a PA-MPJPE of 5.5mm and a PA-MPVPE of 5.0mm. As for performance speed, our method reached up to 33 frames per second (fps) when using HRNet and up to 70 fps when employing FastViT-MA36

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="2403.01813")

Code

Syntology Ran 1 of 15 code samples harvested from 1 repository linked to this paper; 14 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: community (archive-listed): 15 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

patiencefromzhou/simplehand 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

15 samples harvested; 1 ran; 0 honoured the contract we drafted; 14 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
14unverified

Licence: 0 of the 15 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 patiencefromzhou/simplehand. “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.

align_w_scale patiencefromzhou/simplehand/infer_to_json.py community (archive-listed) ran fingerprinted MIT (permissive) · 38a4447a0132916a · report
build_position_encoding patiencefromzhou/simplehand/models/position_embedding.py community (archive-listed) unverified MIT (permissive) · e75bcdbf04de72fc · report
get_fingertip patiencefromzhou/simplehand/models/losses.py community (archive-listed) unverified MIT (permissive) · 815a62ae24a7fc21 · report
get_points_bbox patiencefromzhou/simplehand/kp_preprocess.py community (archive-listed) unverified MIT (permissive) · 0bf60765ad37025b · report
get_points_center_scale patiencefromzhou/simplehand/kp_preprocess.py community (archive-listed) unverified MIT (permissive) · 389ba32a8050a643 · report
keypoint_auc patiencefromzhou/simplehand/eval_utils.py community (archive-listed) unverified MIT (permissive) · 07fc37b1ec3cad9d · report
keypoint_pck_accuracy patiencefromzhou/simplehand/eval_utils.py community (archive-listed) unverified MIT (permissive) · 13917732e49d58d9 · report
lbs patiencefromzhou/simplehand/models/mano_torch.py community (archive-listed) unverified MIT (permissive) · 0799d9a300d22e21 · report
load_mano_params_c patiencefromzhou/simplehand/models/losses.py community (archive-listed) unverified MIT (permissive) · f97abd9a3ca74542 · report
pose_pck_accuracy patiencefromzhou/simplehand/eval_utils.py community (archive-listed) unverified MIT (permissive) · 1513953f7add59bd · report
preprocess patiencefromzhou/simplehand/kp_preprocess.py community (archive-listed) unverified MIT (permissive) · 22857b95dac1ddca · report
project_k patiencefromzhou/simplehand/models/losses.py community (archive-listed) unverified MIT (permissive) · 6169d0071af029b3 · report
read_info patiencefromzhou/simplehand/dataset.py community (archive-listed) unverified MIT (permissive) · ed3e5078d9be2fe8 · report
remap_uv patiencefromzhou/simplehand/models/modules.py community (archive-listed) unverified MIT (permissive) · 1f941eb6db919207 · report
vertices2landmarks patiencefromzhou/simplehand/models/mano_torch.py community (archive-listed) unverified MIT (permissive) · f60c90a51b7481f7 · report

Tasks

3D Hand Pose EstimationComputational EfficiencyGesture RecognitionHand Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Hand Pose Estimation DexYCB SimpleHand Average MPJPE (mm) 12.4 #3 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB SimpleHand MPVPE 12.1 #3 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB SimpleHand PA-MPVPE 5.5 #3 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB SimpleHand PA-VAUC - #3 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB SimpleHand Procrustes-Aligned MPJPE 5.5 #3 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB SimpleHand VAUC - #3 of 11 Archive leaderboard report
3D Hand Pose Estimation FreiHAND Zhou et al. PA-F@15mm 0.986 #7 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND Zhou et al. PA-F@5mm 0.772 #7 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND Zhou et al. PA-MPJPE 5.7 #7 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND Zhou et al. PA-MPVPE 6.0 #7 of 33 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

Batch NormalizationConvolutionHRNetReLUResidual Connection

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