Papers › MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image

MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image

6 Dec 2021CVPR 2022 1arXiv:2112.02753archive 2025-07-28

Xingyu Chen, Yufeng Liu, Yajiao Dong, Xiong Zhang, Chongyang Ma, Yanmin Xiong, Yuan Zhang, Xiaoyan Guo

In this work, we propose a framework for single-view hand mesh reconstruction, which can simultaneously achieve high reconstruction accuracy, fast inference speed, and temporal coherence. Specifically, for 2D encoding, we propose lightweight yet effective stacked structures. Regarding 3D decoding, we provide an efficient graph operator, namely depth-separable spiral convolution. Moreover, we present a novel feature lifting module for bridging the gap between 2D and 3D representations. This module begins with a map-based position regression (MapReg) block to integrate the merits of both heatmap encoding and position regression paradigms for improved 2D accuracy and temporal coherence. Furthermore, MapReg is followed by pose pooling and pose-to-vertex lifting approaches, which transform 2D pose encodings to semantic features of 3D vertices. Overall, our hand reconstruction framework, called MobRecon, comprises affordable computational costs and miniature model size, which reaches a high inference speed of 83FPS on Apple A14 CPU. Extensive experiments on popular datasets such as FreiHAND, RHD, and HO3Dv2 demonstrate that our MobRecon achieves superior performance on reconstruction accuracy and temporal coherence. Our code is publicly available at https://github.com/SeanChenxy/HandMesh.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2112.02753")

Code

Syntology Ran 7 of 9 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 5 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

SeanChenxy/HandMesh officialmentioned in papermentioned 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

9 samples harvested; 7 ran; 0 honoured the contract we drafted; 2 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
5ran
2unverified

Licence: 0 of the 9 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 SeanChenxy/HandMesh. “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.

bce_loss SeanChenxy/HandMesh/cmr/models/loss.py official repository ran MIT (permissive) · 0a345c9ad82f11fa · report
conv1x1 SeanChenxy/HandMesh/cmr/models/resnet.py official repository ran · our draft was wrong MIT (permissive) · d9def42110729a85 · report
conv3x3 SeanChenxy/HandMesh/cmr/models/resnet.py official repository ran · our draft was wrong MIT (permissive) · 160bb14bd76201b4 · report
conv_layer SeanChenxy/HandMesh/cmr/models/network_mobrecon.py official repository ran MIT (permissive) · 88c9b7333f9e5e69 · report
l1_loss SeanChenxy/HandMesh/cmr/models/loss.py official repository ran fingerprinted MIT (permissive) · 52873d5d0dc3cad5 · report
linear_layer SeanChenxy/HandMesh/cmr/models/network_mobrecon.py official repository ran MIT (permissive) · a29a058e008b55a9 · report
resnet18 SeanChenxy/HandMesh/cmr/models/resnet.py official repository ran MIT (permissive) · 23b518f1014a72f5 · report
Pool SeanChenxy/HandMesh/cmr/models/network_mobrecon.py official repository unverified MIT (permissive) · 21126d9705e3eae1 · report
normal_loss SeanChenxy/HandMesh/cmr/models/loss.py official repository unverified MIT (permissive) · f82aaf02ccad7316 · report

Tasks

3D Hand Pose EstimationPosition regressionregression

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Hand Pose Estimation DexYCB MobRecon Average MPJPE (mm) 14.2 #8 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB MobRecon MPVPE 13.1 #8 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB MobRecon PA-MPVPE 5.6 #8 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB MobRecon PA-VAUC 88.9 #8 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB MobRecon Procrustes-Aligned MPJPE 6.40 #8 of 11 Archive leaderboard report
3D Hand Pose Estimation DexYCB MobRecon VAUC 76.1 #8 of 11 Archive leaderboard report
3D Hand Pose Estimation FreiHAND MobRecon PA-F@15mm 0.986 #6 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND MobRecon PA-F@5mm 0.784 #6 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND MobRecon PA-MPJPE 5.7 #6 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND MobRecon PA-MPVPE 5.8 #6 of 33 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 MobRecon F@15mm 0.957 #11 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 MobRecon F@5mm 0.538 #11 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 MobRecon PA-MPJPE (mm) 9.2 #11 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 MobRecon PA-MPVPE 9.4 #11 of 24 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

HeatmapSPEED

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