SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.03244 · 2019

Convolutional Mesh Regression for Single-Image Human Shape Reconstruction

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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 2 have no contract verdict; 4 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/1905.03244.json · badge: /api/ran/1905.03244.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
nkolot/GraphCMR community (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
FunctionStatusWhere it lives
batch_svd Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
nkolot/GraphCMR/models/smpl_param_regressor.py
code served (permissive licence) · get_code("6697b1ba4e63ee2a")
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)

# Create a batch of matrices
# batch_svd expects A to be a 3D tensor where:
# - A.shape[0] is the batch size
# - A[i] is a 2D matrix for SVD decomposition
# Using batch_size=2, matrix dimensions 4x3 for distinctness
batch_size = 2
rows = 4
cols = 3

A = torch.randn(batch_size, rows, cols)

ARGS = {
    "A": A
}
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
orthographic_projection Ran
ran on a synthesized input
nkolot/GraphCMR/models/geometric_layers.py
code served (permissive licence) · get_code("e6704260d6ef70f5")
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, 4, 2) 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)

# X: size = [B, N, 3] where B is batch size, N is number of points
# camera: size = [B, 3] where B is batch size, 3 contains [scale, tx, ty]

B = 2  # batch size
N = 4  # number of points
X = torch.randn(B, N, 3)
camera = torch.randn(B, 3)

ARGS = {
    "X": X,
    "camera": camera,
}
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, 4, 2) — shape (2, 4, 2) 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
nkolot/GraphCMR/models/geometric_layers.py
code served (permissive licence) · get_code("baa1c1737c3796df")
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 quat2mat expects a quaternion tensor of shape [B, 4]
# where B is batch size and 4 represents (w, x, y, z) components
# Create a small batch of 2 quaternions
quat = torch.randn(2, 4)

ARGS = {
    "quat": quat
}
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
resnet50 Ran
ran; our contract draft was wrong, not the code
nkolot/GraphCMR/models/resnet.py
code served (permissive licence) · get_code("60f5ad28853bf17c")
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 ResNet. 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 = {
    'pretrained': False,
}
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 ResNet — a ResNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ResNet output the recorded ndim 0 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
rodrigues Ran
ran; our contract draft was wrong, not the code
nkolot/GraphCMR/models/geometric_layers.py
code served (permissive licence) · get_code("c15f1cb769ff504f")
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 rodrigues takes theta as input
# theta: size = [B, 3] - batch of axis-angle representations
# The function uses:
# - torch.norm(theta + 1e-08, p=2, dim=1)
# - torch.unsqueeze(l1norm, -1)
# - torch.div(theta, angle)
# - torch.cos(angle)
# - torch.sin(angle)
# - torch.cat([v_cos, v_sin * normalized], dim=1)
# - quat2mat(quat) where quat has size [B, 4]

# Create a batch of axis-angle representations
# Batch size: 2, each axis-angle vector has 3 components
theta = torch.randn(2, 3)

ARGS = {
    "theta": theta
}
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
spmm Ran
ran on a synthesized input
nkolot/GraphCMR/models/graph_layers.py
code served (permissive licence) · get_code("9b987af9445edb28")
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 sparse matrix (2x3)
sparse = torch.sparse_coo_tensor(
    indices=torch.tensor([[0, 1], [0, 2]]),
    values=torch.tensor([1.0, 2.0]),
    size=(2, 3)
)

# Create a small dense matrix (3x4) with requires_grad=True
dense = torch.randn(3, 4, requires_grad=True)

ARGS = {
    "sparse": sparse,
    "dense": dense,
}
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
create_dataset Not yet run
unverified (harvested, no recorded run)
nkolot/GraphCMR/datasets/datasets.py
code served (permissive licence) · get_code("1f48c41b52133a85")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 6 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 6 later) and 1 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
resnet50 13 other papers
1 dated earlier, 12 later
1603.04992 (2016-03)
Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue
2006.05734 (2020-06)
3D Human Mesh Regression with Dense Correspondence
2106.09017 (2021-06)
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation
and 10 more not named here
quat2mat 7 other papers
7 later
2004.01946 (2020-04)
Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild
2006.05734 (2020-06)
3D Human Mesh Regression with Dense Correspondence
2108.06819 (2021-08)
EventHPE: Event-based 3D Human Pose and Shape Estimation
and 4 more not named here
orthographic_projection 6 other papers
6 later
2004.01946 (2020-04)
Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild
2006.05734 (2020-06)
3D Human Mesh Regression with Dense Correspondence
2010.16143 (2020-10)
HyperText: Endowing FastText with Hyperbolic Geometry
and 3 more not named here
rodrigues 4 other papers
4 later
2004.01946 (2020-04)
Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild
2006.05734 (2020-06)
3D Human Mesh Regression with Dense Correspondence
and 1 more not named here
spmm 4 other papers
4 later
2111.08176 (2021-11)
Coarse-to-fine Animal Pose and Shape Estimation
2207.12824 (2022-07)
Compositional Human-Scene Interaction Synthesis with Semantic Control
2211.08805 (2022-11)
Interacting Hand-Object Pose Estimation via Dense Mutual Attention
and 1 more not named here
batch_svd 1 other paper
1 later
2207.13820 (2022-07)
Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery 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

This paper addresses the problem of 3D human pose and shape estimation from a single image. Previous approaches consider a parametric model of the human body, SMPL, and attempt to regress the model parameters that give rise to a mesh consistent with image evidence. This parameter regression has been a very challenging task, with model-based approaches underperforming compared to nonparametric solutions in terms of pose estimation. In our work, we propose to relax this heavy reliance on the model's parameter space. We still retain the topology of the SMPL template mesh, but instead of predicting model parameters, we directly regress the 3D location of the mesh vertices. This is a heavy task for a typical network, but our key insight is that the regression becomes significantly easier using a Graph-CNN. This architecture allows us to explicitly encode the template mesh structure within the network and leverage the spatial locality the mesh has to offer. Image-based features are attached to the mesh vertices and the Graph-CNN is responsible to process them on the mesh structure, while the regression target for each vertex is its 3D location. Having recovered the complete 3D geometry of the mesh, if we still require a specific model parametrization, this can be reliably regressed from the vertices locations. We demonstrate the flexibility and the effectiveness of our proposed graph-based mesh regression by attaching different types of features on the mesh vertices. In all cases, we outperform the comparable baselines relying on model parameter regression, while we also achieve state-of-the-art results among model-based pose estimation approaches.

For agents

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

get_harvested_code_for_paper("1905.03244")
get_code_for_paper("1905.03244")
have("1905.03244")

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

curl https://syntology.ai/api/ran/1905.03244.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.03244.svg)](https://syntology.ai/paper/1905.03244)

Connect an agent — have() is free.