SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.10013 · 2020

Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild

arXiv · PDF · Open in the Atlas

Code that ran

8 of 9 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 6 have no contract verdict; 2 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/2009.10013.json · badge: /api/ran/2009.10013.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
akashsengupta1997/STRAPS-3DHumanShapePose canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
FunctionStatusWhere it lives
augment_cam_t Ran
ran on a synthesized input
akashsengupta1997/STRAPS-3DHumanShapePose/augmentation/cam_augmentation.py
code served (permissive licence) · get_code("bf07dbcf9a0d09a5")
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, 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)

# mean_cam_t should be a tensor with shape (batch_size, 3)
# where batch_size=2 and the 3 elements represent camera translation (tx, ty, tz)
mean_cam_t = torch.randn(2, 3)

# xy_std controls standard deviation for x,y perturbations
xy_std = 0.05

# delta_z_range controls the range for z perturbations
delta_z_range = [-5, 5]

ARGS = {
    "mean_cam_t": mean_cam_t,
    "xy_std": xy_std,
    "delta_z_range": delta_z_range,
}
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, 3) — shape (2, 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
akashsengupta1997/STRAPS-3DHumanShapePose/models/resnet.py
code served (permissive licence) · get_code("d9def42110729a85")
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) and returned Conv2d. 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)

# The function conv1x1 takes in_planes, out_planes, and stride as parameters
# It returns an nn.Conv2d layer configured for 1x1 convolution
# We need to provide valid integer arguments for these parameters

ARGS = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
akashsengupta1997/STRAPS-3DHumanShapePose/models/resnet.py
code served (permissive licence) · get_code("160bb14bd76201b4")
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) and returned Conv2d. 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 = {
    "in_planes": 3,
    "out_planes": 64,
    "stride": 1,
    "groups": 1,
    "dilation": 1,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
normal_sample_shape Ran
ran on a synthesized input
akashsengupta1997/STRAPS-3DHumanShapePose/augmentation/smpl_augmentation.py
code served (permissive licence) · get_code("8c6a10564907b6ec")
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, 10) 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)

batch_size = 2
mean_shape = torch.randn(10, device='cpu')
std_vector = torch.ones(10, device='cpu') * 0.1

ARGS = {
    'batch_size': batch_size,
    'mean_shape': mean_shape,
    'std_vector': std_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 Tensor, ndim 2, dtype family float, shape (2, 10) — shape (2, 10) 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
random_joints2D_deviation Ran
ran on a synthesized input
akashsengupta1997/STRAPS-3DHumanShapePose/augmentation/proxy_rep_augmentation.py
code served (permissive licence) · get_code("7b209907d4a06a91")
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, 17, 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)

# The function expects:
# - joints2D: (batch_size, num_joints, 2) tensor containing 2D joint coordinates
# - delta_j2d_dev_range: list of [min, max] for uniform noise on other joints
# - delta_j2d_hip_dev_range: list of [min, max] for uniform noise on hip joints

# Create a small tensor with shape (batch_size=2, num_joints=17, coordinates=2)
# 17 joints is standard (0-16, with hip joints at indices 11, 12)
joints2D = torch.randn(2, 17, 2, dtype=torch.float32)

ARGS = {
    "joints2D": joints2D,
    "delta_j2d_dev_range": [-5, 5],
    "delta_j2d_hip_dev_range": [-15, 15]
}
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, 17, 2) — shape (2, 17, 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
random_remove_bodyparts Ran
ran on a synthesized input
akashsengupta1997/STRAPS-3DHumanShapePose/augmentation/proxy_rep_augmentation.py
code served (permissive licence) · get_code("2915fd4f3c803791")
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 SegArray. 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 numpy as np
import torch

torch.manual_seed(0)

# Create a small segmentation tensor (batch_size=2, height=4, width=4)
# Values represent class indices, with 0 being background
seg = np.array([
    [[0, 1, 2, 1],
     [1, 2, 1, 0],
     [2, 1, 0, 2],
     [1, 0, 2, 1]],
    [[0, 3, 1, 3],
     [3, 1, 3, 0],
     [1, 3, 0, 1],
     [3, 0, 1, 3]]
], dtype=np.int64)

# Add clone method to numpy array for compatibility
class SegArray(np.ndarray):
    def clone(self):
        return self.copy()

seg = seg.view(SegArray)

# Classes to remove (e.g., bodypart classes 1, 2, 3)
classes_to_remove = [1, 2, 3]

# Probabilities of removal for each class
probabilities_to_remove = [0.5, 0.3, 0.7]

ARGS = {
    "seg": seg,
    "classes_to_remove": classes_to_remove,
    "probabilities_to_remove": probabilities_to_remove
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SegArray — a SegArray output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SegArray output the recorded ndim 3 and dtype family int 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
random_verts2D_deviation Ran
ran on a synthesized input
akashsengupta1997/STRAPS-3DHumanShapePose/augmentation/proxy_rep_augmentation.py
code served (permissive licence) · get_code("b0b26702d02e5ff2")
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, 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:
# - vertices: tensor of shape (bs, 6890, 3) containing 3D vertex coordinates
# - delta_verts2d_dev_range: list of [low, high] for uniform noise range

# Create a small batch of vertices
batch_size = 2
num_verts = 4  # Small number instead of 6890
vertices = torch.randn(batch_size, num_verts, 3)

# Define the noise range
delta_verts2d_dev_range = [-0.01, 0.01]

ARGS = {
    "vertices": vertices,
    "delta_verts2d_dev_range": delta_verts2d_dev_range,
}
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, 3) — shape (2, 4, 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
uniform_sample_shape Ran
ran on a synthesized input
akashsengupta1997/STRAPS-3DHumanShapePose/augmentation/smpl_augmentation.py
code served (permissive licence) · get_code("6610466c7928a546")
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, 10) 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)

batch_size = 2
mean_shape = torch.randn(10, device=torch.device('cpu'))
delta_betas_range = (-0.5, 0.5)

ARGS = {
    'batch_size': batch_size,
    'mean_shape': mean_shape,
    'delta_betas_range': delta_betas_range
}
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, 10) — shape (2, 10) 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
resnet18 Not yet run
unverified (harvested, no recorded run)
akashsengupta1997/STRAPS-3DHumanShapePose/models/resnet.py
code served (permissive licence) · get_code("055a5e7106b48fd2")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 2 the same month, 3 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
conv1x1 431 other papers
97 dated earlier, 3 the same month, 330 later, 1 undated · 38 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1506.01186 (2015-06)
Cyclical Learning Rates for Training Neural Networks
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
and 428 more not named here
conv3x3 312 other papers
53 dated earlier, 3 the same month, 255 later, 1 undated · 31 only as an assembly brick
1409.1556 (2014-09)
Very Deep Convolutional Networks for Large-Scale Image Recognition
1507.05717 (2015-07)
An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition
1512.03385 (2015-12)
Deep Residual Learning for Image Recognition
and 309 more not named here
resnet18 3 other papers
3 later
2108.00351 (2021-08)
LASOR: Learning Accurate 3D Human Pose and Shape Via Synthetic Occlusion-Aware Data and Neural Mesh Rendering
2110.00990 (2021-10)
Hierarchical Kinematic Probability Distributions for 3D Human Shape and Pose Estimation from Images in the Wild
2305.06968 (2023-05)
HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation

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 monocular 3D human shape and pose estimation from an RGB image. Despite great progress in this field in terms of pose prediction accuracy, state-of-the-art methods often predict inaccurate body shapes. We suggest that this is primarily due to the scarcity of in-the-wild training data with diverse and accurate body shape labels. Thus, we propose STRAPS (Synthetic Training for Real Accurate Pose and Shape), a system that utilises proxy representations, such as silhouettes and 2D joints, as inputs to a shape and pose regression neural network, which is trained with synthetic training data (generated on-the-fly during training using the SMPL statistical body model) to overcome data scarcity. We bridge the gap between synthetic training inputs and noisy real inputs, which are predicted by keypoint detection and segmentation CNNs at test-time, by using data augmentation and corruption during training. In order to evaluate our approach, we curate and provide a challenging evaluation dataset for monocular human shape estimation, Sports Shape and Pose 3D (SSP-3D). It consists of RGB images of tightly-clothed sports-persons with a variety of body shapes and corresponding pseudo-ground-truth SMPL shape and pose parameters, obtained via multi-frame optimisation. We show that STRAPS outperforms other state-of-the-art methods on SSP-3D in terms of shape prediction accuracy, while remaining competitive with the state-of-the-art on pose-centric datasets and metrics.

For agents

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

get_harvested_code_for_paper("2009.10013")
get_code_for_paper("2009.10013")
have("2009.10013")

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

curl https://syntology.ai/api/ran/2009.10013.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.10013.svg)](https://syntology.ai/paper/2009.10013)

Connect an agent — have() is free.