SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1705.03098 · 2017

A simple yet effective baseline for 3d human pose estimation

arXiv · PDF · Open in the Atlas

Code that ran

5 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, 1 violated it and 0 have no contract verdict; 4 failures of our instrument; 2 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/1705.03098.json · badge: /api/ran/1705.03098.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
sidify/3d-pose-estimation canonical (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
ZHONGCHUYUN/3d_pose_baseline_tf canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
SJTU-DL-lab/3d-pose-baseline canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
angle_between Ran
ran; our contract draft was wrong, not the code
sidify/3d-pose-estimation/src/kinematics.py
code served (permissive licence) · get_code("c9e9ff520e9b4533")
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 float, ndim 0, dtype family float, shape () 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 math as m

def dotproduct(v1, v2):
    return sum((a * b for a, b in zip(v1, v2)))

def length(v):
    return m.sqrt(dotproduct(v, v))

def angle_between(v1, v2):
    angle = m.acos(dotproduct(v1, v2) / (length(v1) * length(v2))) * 180 / m.pi
    return angle

# Construct valid vectors for angle_between
# The function expects two vectors that can be zipped together
# and computes the angle between them in degrees

v1 = [1.0, 0.0, 0.0, 0.0]
v2 = [0.0, 1.0, 0.0, 0.0]

ARGS = {
    "v1": v1,
    "v2": v2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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
dotproduct Ran
ran, violated the contract we drafted
sidify/3d-pose-estimation/src/kinematics.py
code served (permissive licence) · get_code("2b344ab200743c2d")
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 float, ndim 0, dtype family float, shape () 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
import numpy as np

torch.manual_seed(0)

# The function dotproduct takes two iterables v1 and v2
# and computes the sum of element-wise products by zipping them together.
# The simplest case is to pass two lists or sequences of numbers.

v1 = [1.0, 2.0, 3.0, 4.0]
v2 = [5.0, 6.0, 7.0, 8.0]

ARGS = {
    "v1": v1,
    "v2": v2,
}
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 float, ndim 0, dtype family float, shape () — shape () 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
get_action_subset Ran
ran; our contract draft was wrong, not the code
sidify/3d-pose-estimation/src/predict_3dpose.py
code served (permissive licence) · get_code("f5eee6f4a7a2d3ce")
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 dict. 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 numpy as np

torch.manual_seed(0)

# Create a sample poses_set dictionary
# Keys are tuples of (subject, action, seqname)
# Values are nxd matrices (numpy arrays or tensors representing poses)

poses_set = {
    ("subject_1", "walking", "seq_001"): np.random.randn(10, 4),
    ("subject_1", "running", "seq_002"): np.random.randn(8, 4),
    ("subject_2", "walking", "seq_003"): np.random.randn(12, 4),
    ("subject_2", "jumping", "seq_004"): np.random.randn(6, 4),
    ("subject_3", "walking", "seq_005"): np.random.randn(9, 4),
}

action = "walking"

ARGS = {
    "poses_set": poses_set,
    "action": action,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
length Ran
ran; our contract draft was wrong, not the code
sidify/3d-pose-estimation/src/kinematics.py
code served (permissive licence) · get_code("c98211090c8cd833")
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 float, ndim 0, dtype family float, shape () 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 math as m

def dotproduct(v1, v2):
    return sum((a * b for a, b in zip(v1, v2)))

def length(v):
    return m.sqrt(dotproduct(v, v))

# The function 'length' takes a single parameter 'v' which is used in:
# 1. dotproduct(v, v) - it's passed twice to dotproduct
# 2. dotproduct expects iterables that can be zipped together
# So 'v' should be a sequence of numbers (list, tuple, or iterable)

ARGS = {
    "v": [1.0, 2.0, 3.0, 4.0]
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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
show_anim_curves Ran
ran; our contract draft was wrong, not the code
ZHONGCHUYUN/3d_pose_baseline_tf/src/openpose_3dpose_sandbox.py
code served (permissive licence) · get_code("a5dc69f01bac53c1")
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 module. 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 matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt

# Construct anim_dict
# The function accesses val[:, o] and val[:, o+1] for o in range(0, 36, 2)
# This means val needs to have at least 36 columns
# val comes from np.array(list(anim_dict.values()))
# So anim_dict.values() should produce arrays/lists that when stacked give shape (n_frames, 36+)

anim_dict = {
    f"frame_{i}": np.random.randn(37) for i in range(10)
}

# Create a mock plt object (using actual matplotlib)
_plt = plt

ARGS = {
    "anim_dict": anim_dict,
    "_plt": _plt
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type module — a module output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a module 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
normalization_stats Not yet run
unverified (harvested, no recorded run)
SJTU-DL-lab/3d-pose-baseline/src/data_utils.py
code served (permissive licence) · get_code("9088d315ea27a453")
How it ran

no invocation recorded.

read_openpose_json Not yet run
unverified (harvested, no recorded run)
ZHONGCHUYUN/3d_pose_baseline_tf/src/openpose_3dpose_sandbox.py
code served (permissive licence) · get_code("6bbbd96794d5994d")
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, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 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
get_action_subset 2 other papers
2 later
1711.08585 (2017-11)
Exploiting temporal information for 3D pose estimation
1904.05547 (2019-04)
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network
dotproduct 1 other paper
1 later
2112.11593 (2021-12)
AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation
normalization_stats 1 other paper
1 later
1904.05547 (2019-04)
Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network

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

Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels. Despite their excellent performance, it is often not easy to understand whether their remaining error stems from a limited 2d pose (visual) understanding, or from a failure to map 2d poses into 3-dimensional positions. With the goal of understanding these sources of error, we set out to build a system that given 2d joint locations predicts 3d positions. Much to our surprise, we have found that, with current technology, "lifting" ground truth 2d joint locations to 3d space is a task that can be solved with a remarkably low error rate: a relatively simple deep feed-forward network outperforms the best reported result by about 30\% on Human3.6M, the largest publicly available 3d pose estimation benchmark. Furthermore, training our system on the output of an off-the-shelf state-of-the-art 2d detector (\ie, using images as input) yields state of the art results -- this includes an array of systems that have been trained end-to-end specifically for this task. Our results indicate that a large portion of the error of modern deep 3d pose estimation systems stems from their visual analysis, and suggests directions to further advance the state of the art in 3d human pose estimation.

For agents

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

get_harvested_code_for_paper("1705.03098")
get_code_for_paper("1705.03098")
have("1705.03098")

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

curl https://syntology.ai/api/ran/1705.03098.json

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

[![Syntology run record](https://syntology.ai/api/ran/1705.03098.svg)](https://syntology.ai/paper/1705.03098)

Connect an agent — have() is free.