SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.00988 · ICCV · 2023

HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learning

Jingyu Wang, Pengfei Ren, Zhou Xue, Xiaozheng Zheng, Chao

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 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; 0 honoured the contract we drafted, 0 violated it and 4 have no contract verdict; 7 failures of our instrument; 1 no recorded run), measured 2026-11-22; 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/2302.00988.json · badge: /api/ran/2302.00988.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
zxz267/HaMuCo canonical (classifier label)
classifier basis not recorded on the link
11 ran · 1 no recorded run
FunctionStatusWhere it lives
batch_rodrigues Ran
ran; our contract draft was wrong, not the code
zxz267/HaMuCo/manopth/rodrigues_layer.py
pointer only (licence: MIT); the stored copy get_code serves, from reyuwei/PIANO_model, is pointer only (licence: NONE) · get_code("dba91b8424db46e4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from reyuwei/PIANO_model, and GitHub detected no licence in that repository when it was checked. 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.

batch_rotprojs Ran
ran on a synthesized input
zxz267/HaMuCo/manopth/rotproj.py
code served (permissive licence) · get_code("38b7b3fb9808ec35")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 2, 3, 3) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects batches_rotmats to be a list of batches,
# where each batch contains rotation matrices (3x3).
# We'll create a simple structure: list of batches, each batch is a list of 3x3 rotation matrices.

# Create a few small 3x3 rotation matrices
def create_rotation_matrix():
    """Create a simple rotation matrix via SVD projection"""
    random_mat = torch.randn(3, 3)
    U, S, V = random_mat.svd()
    rotmat = torch.matmul(U, V.transpose(0, 1))
    return rotmat

# Build batches_rotmats as a list of 2 batches, each with 2 rotation matrices
batch_1 = [create_rotation_matrix() for _ in range(2)]
batch_2 = [create_rotation_matrix() for _ in range(2)]
batches_rotmats = [batch_1, batch_2]

ARGS = {
    "batches_rotmats": batches_rotmats
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 2, 3, 3) — shape (2, 2, 3, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compute_rotation_matrix_from_ortho6d Ran
ran; our contract draft was wrong, not the code
zxz267/HaMuCo/manopth/rot6d.py
code served (permissive licence) · get_code("a38b0a9ed5b07f1e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 3, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects a batch of 6D pose vectors (batch_size, 6)
# where first 3 elements represent x_raw and last 3 represent y_raw
poses = torch.randn(2, 6)

ARGS = {
    "poses": poses
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 3, 3) — shape (2, 3, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
make_conv1d_layers Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zxz267/HaMuCo/models/module.py
code served (permissive licence) · get_code("41843763717707cc")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Sequential. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "feat_dims": [3, 16, 32, 64],
    "kernel": 3,
    "stride": 1,
    "padding": 1,
    "bnrelu_final": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
make_conv_layers Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zxz267/HaMuCo/models/module.py
pointer only (licence: MIT); the stored copy get_code serves, from dqj5182/contho_release, is pointer only (licence: NOASSERTION) · get_code("622140af456ff5d2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from dqj5182/contho_release, and GitHub could not classify the licence of that repository (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.

make_linear_layers Ran
ran; our contract draft was wrong, not the code
zxz267/HaMuCo/models/module.py
pointer only (licence: MIT); the stored copy get_code serves, from dqj5182/contho_release, is pointer only (licence: NOASSERTION) · get_code("6309528f3f76d031")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from dqj5182/contho_release, and GitHub could not classify the licence of that repository (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.

normalize_vector Ran
ran on a synthesized input
zxz267/HaMuCo/manopth/rot6d.py
code served (permissive licence) · get_code("3805fbcc04dcc429")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create a small batch of vectors to normalize
# batch size: 2, vector dimension: 4
v = torch.randn(2, 4)

ARGS = {
    "v": v
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
quat2mat Ran
ran; our contract draft was wrong, not the code
zxz267/HaMuCo/manopth/rodrigues_layer.py
pointer only (licence: MIT); the stored copy get_code serves, from reyuwei/PIANO_model, is pointer only (licence: NONE) · get_code("bec37e39340a8433")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from reyuwei/PIANO_model, and GitHub detected no licence in that repository when it was checked. 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.

robust_compute_rotation_matrix_from_ortho6d Ran
ran on a synthesized input
zxz267/HaMuCo/manopth/rot6d.py
code served (permissive licence) · get_code("654590121b6d9091")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 3, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects poses to be a tensor of shape (batch_size, 6)
# where the first 3 elements are x_raw and the last 3 are y_raw
batch_size = 2
poses = torch.randn(batch_size, 6)

ARGS = {
    "poses": poses
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 3, 3) — shape (2, 3, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
th_get_axis_angle Ran
ran on a synthesized input
zxz267/HaMuCo/manopth/rodrigues_layer.py
code served (permissive licence) · get_code("3329bdb6aefcb48f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects a 2D tensor where:
# - dimension 0 is the batch size
# - dimension 1 is the vector dimension
# The function computes norm along dimension 1, so we need batch_size x vector_dim

vector = torch.randn(2, 4)

ARGS = {
    "vector": vector,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
th_pack Ran
ran; our contract draft was wrong, not the code
zxz267/HaMuCo/manopth/tensutils.py
pointer only (licence: MIT); the stored copy get_code serves, from reyuwei/PIANO_model, is pointer only (licence: NONE) · get_code("a012fac19e3c7477")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from reyuwei/PIANO_model, and GitHub detected no licence in that repository when it was checked. 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.

th_with_zeros Not yet run
unverified (harvested, no recorded run)
zxz267/HaMuCo/manopth/tensutils.py
pointer only (licence: MIT); the stored copy get_code serves, from reyuwei/PIANO_model, is pointer only (licence: NONE) · get_code("cd37580add3ccba5")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from reyuwei/PIANO_model, and GitHub detected no licence in that repository when it was checked. 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 8 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 8 later) and 4 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
make_conv_layers 12 other papers
3 dated earlier, 8 later, 1 same year, order not determinable
2008.03713 (2020-08)
I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image
2104.07300 (2021-04)
Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes
2211.08805 (2022-11)
Interacting Hand-Object Pose Estimation via Dense Mutual Attention
and 9 more not named here
make_linear_layers 9 other papers
2 dated earlier, 6 later, 1 same year, order not determinable
2008.03713 (2020-08)
I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image
2104.07300 (2021-04)
Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes
and 6 more not named here
make_conv1d_layers 6 other papers
2 dated earlier, 3 later, 1 same year, order not determinable
2008.03713 (2020-08)
I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image
2104.07300 (2021-04)
Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes
and 3 more not named here
quat2mat 4 other papers
2 dated earlier, 2 later
2106.10893 (2021-06)
PIANO: A Parametric Hand Bone Model from Magnetic Resonance Imaging
2209.07589 (2022-09)
PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Tracking
2308.10305 (2023-08)
Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video
and 1 more not named here
batch_rodrigues 3 other papers
1 dated earlier, 2 later
2106.10893 (2021-06)
PIANO: A Parametric Hand Bone Model from Magnetic Resonance Imaging
2308.10305 (2023-08)
Co-Evolution of Pose and Mesh for 3D Human Body Estimation from Video
2309.09301 (2023-09)
RenderIH: A Large-scale Synthetic Dataset for 3D Interacting Hand Pose Estimation
th_pack 2 other papers
1 dated earlier, 1 later
2106.10893 (2021-06)
PIANO: A Parametric Hand Bone Model from Magnetic Resonance Imaging
2303.05938 (2023-03)
ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction
th_with_zeros 2 other papers
1 dated earlier, 1 later
2106.10893 (2021-06)
PIANO: A Parametric Hand Bone Model from Magnetic Resonance Imaging
2303.05938 (2023-03)
ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction
compute_rotation_matrix_from_ortho6d 1 other paper
1 later
2303.08240 (2023-03)
Parametric Surface Constrained Upsampler Network for Point Cloud

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

Recent advancements in 3D hand pose estimation have shown promising results, but its effectiveness has primarily relied on the availability of large-scale annotated datasets, the creation of which is a laborious and costly process. To alleviate the label-hungry limitation, we propose a selfsupervised learning framework, HaMuCo, that learns a single-view hand pose estimator from multi-view pseudo 2D labels. However, one of the main challenges of selfsupervised learning is the presence of noisy labels and the "groupthink" effect from multiple views. To overcome these issues, we introduce a cross-view interaction network that distills the single-view estimator by utilizing the cross-view correlated features and enforcing multi-view consistency to achieve collaborative learning. Both the single-view estimator and the cross-view interaction network are trained jointly in an end-to-end manner. Extensive experiments show that our method can achieve state-of-the-art performance on multi-view self-supervised hand pose estimation. Furthermore, the proposed cross-view interaction network can also be applied to hand pose estimation from multi-view input and outperforms previous methods under the same settings.

For agents

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

get_harvested_code_for_paper("2302.00988")
get_code_for_paper("2302.00988")
have("2302.00988")

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

curl https://syntology.ai/api/ran/2302.00988.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.00988.svg)](https://syntology.ai/paper/2302.00988)

Connect an agent — have() is free.