SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.09646 · NeurIPS · 2024

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

Aviral Chharia, Fernando De La Torre, Haoye Dong, Wenbo Gou, Francisco Carrasco

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 3 failures of our instrument; 4 no recorded run), measured 2026-11-22; 1 contract verdicts on these samples were measured on the host before the contract probe was jailed (2026-09-18T14:29:13Z) or are undated; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2407.09646.json · badge: /api/ran/2407.09646.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
humansensinglab/Hamba canonical (classifier label)
classifier basis: classifier_2025
7 ran · 4 no recorded run
FunctionStatusWhere it lives
Discriminator Ran
ran on a synthesized input
humansensinglab/Hamba/hamba/models/hamba.py
pointer only (licence: NOASSERTION) · get_code("337932b7fd64e115")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, humansensinglab/Hamba (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

GridSampleFeature Ran
ran on a synthesized input
humansensinglab/Hamba/hamba/models/hamba.py
pointer only (licence: NOASSERTION) · get_code("4ab23a8b84bc730f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, humansensinglab/Hamba (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

aa_to_rotmat Ran
ran, honoured the contract we drafted
humansensinglab/Hamba/hamba/models/hamba.py
pointer only (licence: NOASSERTION) · get_code("554ba28f99249e6a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, humansensinglab/Hamba (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_pylogger Ran
ran; our contract draft was wrong, not the code
humansensinglab/Hamba/hamba/models/hamba.py
pointer only (licence: NOASSERTION) · get_code("aebb727eed75bd10")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, humansensinglab/Hamba (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

load_pred_json Ran
ran; our contract draft was wrong, not the code
humansensinglab/Hamba/eval/freihand/eval_freihand_official.py
pointer only (licence: NOASSERTION) · get_code("5e826097a94f6d97")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, humansensinglab/Hamba (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

perspective_projection Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
humansensinglab/Hamba/hamba/models/hamba.py
pointer only (licence: NOASSERTION) · get_code("7821cfe9fbd23004")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, humansensinglab/Hamba (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

quat_to_rotmat Ran
ran, honoured the contract we drafted
humansensinglab/Hamba/hamba/models/hamba.py
pointer only (licence: NOASSERTION) · get_code("dcf1f2ee89252c02")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, humansensinglab/Hamba (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

HAMBA Not yet run
unverified (harvested, no recorded run)
humansensinglab/Hamba/hamba/models/hamba.py
pointer only (licence: NOASSERTION) · get_code("ba1473b03e5c5603")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, humansensinglab/Hamba (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

calculate_fscore Not yet run
unverified (harvested, no recorded run)
humansensinglab/Hamba/eval/freihand/eval_freihand_official.py
pointer only (licence: NOASSERTION) · get_code("a5d914926ce4fb86")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, humansensinglab/Hamba (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

create_backbone Not yet run
unverified (harvested, no recorded run)
humansensinglab/Hamba/hamba/models/hamba.py
pointer only (licence: NOASSERTION) · get_code("a5abb3180cb1201b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, humansensinglab/Hamba (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

verts2pcd Not yet run
unverified (harvested, no recorded run)
humansensinglab/Hamba/eval/freihand/eval_freihand_official.py
pointer only (licence: NOASSERTION) · get_code("13f7fc2776c7ce31")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, humansensinglab/Hamba (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 the same month, 1 later) and 6 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_pylogger
brick of this paper's assembly: helper
14 other papers
11 dated earlier, 3 later · 1 only as an assembly brick
2209.03143 (2022-09)
AudioLM: a Language Modeling Approach to Audio Generation
2305.14930 (2023-05)
In-Context Impersonation Reveals Large Language Models' Strengths and Biases
2305.20091 (2023-05)
Humans in 4D: Reconstructing and Tracking Humans with Transformers
and 11 more not named here
quat_to_rotmat
brick of this paper's assembly: helper
2 other papers
2 dated earlier · 2 only as an assembly brick
2305.20091 (2023-05)
Humans in 4D: Reconstructing and Tracking Humans with Transformers
2403.09623 (2024-03)
Score-Guided Diffusion for 3D Human Recovery
aa_to_rotmat
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2305.20091 (2023-05)
Humans in 4D: Reconstructing and Tracking Humans with Transformers
create_backbone
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2305.20091 (2023-05)
Humans in 4D: Reconstructing and Tracking Humans with Transformers
perspective_projection
brick of this paper's assembly: helper
1 other paper
1 dated earlier · 1 only as an assembly brick
2305.20091 (2023-05)
Humans in 4D: Reconstructing and Tracking Humans with Transformers

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 1 on 3D hand reconstruction.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2407.09646")
get_code_for_paper("2407.09646")
have("2407.09646")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2407.09646.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2407.09646.svg)](https://syntology.ai/paper/2407.09646)

Connect an agent — have() is free.