Papers › Interacting Hand-Object Pose Estimation via Dense Mutual Attention

Interacting Hand-Object Pose Estimation via Dense Mutual Attention

16 Nov 2022arXiv:2211.08805archive 2025-07-28

Rong Wang, Wei Mao, Hongdong Li

3D hand-object pose estimation is the key to the success of many computer vision applications. The main focus of this task is to effectively model the interaction between the hand and an object. To this end, existing works either rely on interaction constraints in a computationally-expensive iterative optimization, or consider only a sparse correlation between sampled hand and object keypoints. In contrast, we propose a novel dense mutual attention mechanism that is able to model fine-grained dependencies between the hand and the object. Specifically, we first construct the hand and object graphs according to their mesh structures. For each hand node, we aggregate features from every object node by the learned attention and vice versa for each object node. Thanks to such dense mutual attention, our method is able to produce physically plausible poses with high quality and real-time inference speed. Extensive quantitative and qualitative experiments on large benchmark datasets show that our method outperforms state-of-the-art methods. The code is available at https://github.com/rongakowang/DenseMutualAttention.git.

PaperPDFCodeCode 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="2211.08805")

Code

Syntology Ran 1 of 5 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran with no contract checked.

By repository: official repository: 5 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.

rongakowang/densemutualattention 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

5 samples harvested; 1 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
4unverified

Licence: 0 of the 5 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 rongakowang/densemutualattention. “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.

make_conv_layers rongakowang/densemutualattention/common/nets/layer.py official repository ran MIT (permissive) · 622140af456ff5d2 · report
make_conv1d_layers rongakowang/densemutualattention/common/nets/layer.py official repository unverified MIT (permissive) · 7028b78d1d3a2f93 · report
make_linear_layers rongakowang/densemutualattention/common/nets/layer.py official repository unverified MIT (permissive) · 7223f94782b5fb61 · report
spmm rongakowang/densemutualattention/common/nets/graph_layers.py official repository unverified MIT (permissive) · 9b987af9445edb28 · report
tensorify rongakowang/densemutualattention/common/utils/collision_loss.py official repository unverified MIT (permissive) · 37ba8c8c54663d90 · report

Tasks

3D Hand Pose EstimationObjectPose Estimationhand-object pose

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Hand Pose Estimation HO-3D v2 DMA PA-MPJPE (mm) 10.1 #14 of 24 Archive leaderboard report
hand-object pose DexYCB DMA ADD-S 15.9 #3 of 9 Archive leaderboard report
hand-object pose DexYCB DMA Average MPJPE (mm) 12.7 #3 of 9 Archive leaderboard report
hand-object pose DexYCB DMA MCE 32.6 #3 of 9 Archive leaderboard report
hand-object pose DexYCB DMA OCE 27.3 #3 of 9 Archive leaderboard report
hand-object pose DexYCB DMA Procrustes-Aligned MPJPE 6.86 #3 of 9 Archive leaderboard report
hand-object pose HO-3D v2 DMA ADD-S 20.8 #2 of 9 Archive leaderboard report
hand-object pose HO-3D v2 DMA Average MPJPE (mm) 22.2 #2 of 9 Archive leaderboard report
hand-object pose HO-3D v2 DMA OME 45.5 #2 of 9 Archive leaderboard report
hand-object pose HO-3D v2 DMA PA-MPJPE 10.1 #2 of 9 Archive leaderboard report
hand-object pose HO-3D v2 DMA ST-MPJPE 23.8 #2 of 9 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