Papers › Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba

Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba

12 Jul 2024arXiv:2407.09646archive 2025-07-28

Haoye Dong, Aviral Chharia, Wenbo Gou, Francisco Vicente Carrasco, Fernando de la Torre

3D Hand reconstruction from a single RGB image is challenging due to the articulated motion, self-occlusion, and interaction with objects. Existing SOTA methods employ attention-based transformers to learn the 3D hand pose and shape, yet they do not fully achieve robust and accurate performance, primarily due to inefficiently modeling spatial relations between joints. To address this problem, we propose a novel graph-guided Mamba framework, named Hamba, which bridges graph learning and state space modeling. Our core idea is to reformulate Mamba's scanning into graph-guided bidirectional scanning for 3D reconstruction using a few effective tokens. This enables us to efficiently learn the spatial relationships between joints for improving reconstruction performance. Specifically, we design a Graph-guided State Space (GSS) block that learns the graph-structured relations and spatial sequences of joints and uses 88.5% fewer tokens than attention-based methods. Additionally, we integrate the state space features and the global features using a fusion module. By utilizing the GSS block and the fusion module, Hamba effectively leverages the graph-guided state space features and jointly considers global and local features to improve performance. Experiments on several benchmarks and in-the-wild tests demonstrate that Hamba significantly outperforms existing SOTAs, achieving the PA-MPVPE of 5.3mm and F@15mm of 0.992 on FreiHAND. At the time of this paper's acceptance, Hamba holds the top position, Rank 1 in two Competition Leaderboards on 3D hand reconstruction. Project Website: https://humansensinglab.github.io/Hamba/

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 1 repository, 7 ran (4 with no instrument failure; 3 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 7 samples that ran has no recorded date.

humansensinglab/Hamba officialmentioned on GitHubpytorchSyntology: 11 samples, 7 ran (3 instrument-failed) · 4 unverified 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

11 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
2ran · our draft was wrong
1ran; the contract check could not run
2ran
4unverified

Licence: 11 of the 11 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 humansensinglab/Hamba. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

humansensinglab/Hamba official repository 11 samples, 7 ran (3 instrument-failed) · 4 unverified
Discriminator in 42 papers hamba/models/hamba.py ran licence not identified · pointer only · 337932b7fd64e115 · report fixture: signature poses:Tensor/4/float, betas:Tensor/2/float · returned Tensor · level recorded 2026-09-24
GridSampleFeature hamba/models/hamba.py ran licence not identified · pointer only · 4ab23a8b84bc730f · report fixture: signature img_feature:Tensor/4/float, joint_uv:Tensor/3/float, mode:str/0/str · returned Tensor · level recorded 2026-09-24
aa_to_rotmat hamba/models/hamba.py ran · honoured contract fingerprinted licence not identified · pointer only · 554ba28f99249e6a · report fixture: signature theta:Tensor/2/float · returned Tensor · level recorded 2026-09-22
get_pylogger in 16 papers hamba/models/hamba.py ran · our draft was wrong licence not identified · pointer only · aebb727eed75bd10 · report fixture: signature name:str/0/str · returned Logger · level recorded 2026-09-22
load_pred_json eval/freihand/eval_freihand_official.py ran · our draft was wrong licence not identified · pointer only · 5e826097a94f6d97 · report fixture: signature filepath:str/0/str · returned tuple · level recorded, date not recorded
perspective_projection in 7 papers hamba/models/hamba.py ran; the contract check could not run (RAISES) licence not identified · pointer only · 7821cfe9fbd23004 · report fixture: signature points:Tensor/3/float, translation:Tensor/2/float, focal_length:Tensor/2/float, camera_center:Tensor/2/float, rotation:Tensor/3/float · returned Tensor · level recorded 2026-09-22
quat_to_rotmat hamba/models/hamba.py ran · honoured contract fingerprinted licence not identified · pointer only · dcf1f2ee89252c02 · report fixture: signature quat:Tensor/2/float · returned Tensor · level recorded 2026-09-22
HAMBA hamba/models/hamba.py unverified licence not identified · pointer only · ba1473b03e5c5603 · report
calculate_fscore eval/freihand/eval_freihand_official.py unverified licence not identified · pointer only · a5d914926ce4fb86 · report
create_backbone hamba/models/hamba.py unverified licence not identified · pointer only · a5abb3180cb1201b · report
verts2pcd eval/freihand/eval_freihand_official.py unverified licence not identified · pointer only · 13f7fc2776c7ce31 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Hamba (graph method: Hamba). 8 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. HAMBA entry · level 0 · unverified · ba1473b03e5c5603
  2. Discriminator helper · level 1 · ran · 337932b7fd64e115
  3. GridSampleFeature helper · level 1 · ran · 4ab23a8b84bc730f
  4. aa_to_rotmat helper · level 1 · ran · honoured contract · 554ba28f99249e6a
  5. create_backbone helper · level 0 · unverified · a5abb3180cb1201b
  6. perspective_projection helper · level 1 · ran; the contract check could not run (RAISES) · 7821cfe9fbd23004
  7. quat_to_rotmat helper · level 1 · ran · honoured contract · dcf1f2ee89252c02
  8. get_pylogger helper · level 1 · ran · our draft was wrong · aebb727eed75bd10

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2407.09646") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D Hand Pose EstimationMamba

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Hand Pose Estimation FreiHAND Hamba PA-F@15mm 0.992 #5 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND Hamba PA-F@5mm 0.806 #5 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND Hamba PA-MPJPE 5.7 #5 of 33 Archive leaderboard report
3D Hand Pose Estimation FreiHAND Hamba PA-MPVPE 5.3 #5 of 33 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild Hamba PCK@0.05 (New Days) All 48.7 #3 of 10 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild Hamba PCK@0.05 (NewDays) Occ 28.2 #3 of 10 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild Hamba PCK@0.05 (NewDays) Visible 61.2 #3 of 10 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild Hamba PCK@0.05 (VISOR) All 47.2 #3 of 10 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild Hamba PCK@0.05 (VISOR) Occ 29.9 #3 of 10 Archive leaderboard report
3D Hand Pose Estimation HInt: Hand Interactions in the wild Hamba PCK@0.05 (VISOR) Visible 61.4 #3 of 10 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 Hamba AUC_J 0.850 #2 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 Hamba AUC_V 0.846 #2 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 Hamba F@15mm 0.982 #2 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 Hamba F@5mm 0.648 #2 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 Hamba PA-MPJPE (mm) 7.5 #2 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v2 Hamba PA-MPVPE 7.7 #2 of 24 Archive leaderboard report
3D Hand Pose Estimation HO-3D v3 Hamba AUC_J 0.861 #1 of 8 Archive leaderboard report
3D Hand Pose Estimation HO-3D v3 Hamba AUC_V 0.864 #1 of 8 Archive leaderboard report
3D Hand Pose Estimation HO-3D v3 Hamba F@15mm 0.982 #1 of 8 Archive leaderboard report
3D Hand Pose Estimation HO-3D v3 Hamba F@5mm 0.681 #1 of 8 Archive leaderboard report
3D Hand Pose Estimation HO-3D v3 Hamba PA-MPJPE 6.9 #1 of 8 Archive leaderboard report
3D Hand Pose Estimation HO-3D v3 Hamba PA-MPVPE 6.8 #1 of 8 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