SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.05754 · 2019

Learnable Triangulation of Human Pose

arXiv · PDF · Open in the Atlas

Code that ran

16 of 17 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 15 have no contract verdict; 1 failure 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/1905.05754.json · badge: /api/ran/1905.05754.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
karfly/learnable-triangulation-pytorch community (classifier label)
classifier basis not recorded on the link
16 ran · 1 no recorded run
FunctionStatusWhere it lives
calc_gradient_norm Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/utils/misc.py
code served (permissive licence) · get_code("c37b9335c3c1e219")
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 torch.nn as nn

torch.manual_seed(0)

# Create a simple neural network module
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

# Instantiate the model
model = SimpleModel()

# Create some dummy input and output
x = torch.randn(2, 4)
y = torch.randn(2, 2)

# Forward pass
output = model(x)

# Compute loss and backward pass to populate gradients
loss_fn = nn.MSELoss()
loss = loss_fn(output, y)
loss.backward()

# Create named_parameters from the model
named_parameters = model.named_parameters()

ARGS = {
    "named_parameters": named_parameters
}
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 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
config_to_str Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/utils/misc.py
code served (permissive licence) · get_code("9e08201135438284")
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 str. 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 yaml
import json

# The function config_to_str takes a config parameter and:
# 1. Converts it to JSON via json.dumps(config)
# 2. Loads it back via yaml.safe_load
# 3. Dumps it as YAML via yaml.dump
# So config needs to be JSON-serializable (dict, list, primitives, etc.)

# Create a valid config dict with various data types
config = {
    "model_name": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "epochs": 10,
    "layers": [64, 128, 256],
    "dropout": 0.5,
    "use_cuda": False,
    "nested": {
        "optimizer": "adam",
        "scheduler": "cosine",
        "params": [1, 2, 3]
    }
}

ARGS = {
    "config": config
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, yaml — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
karfly/learnable-triangulation-pytorch/mvn/models/pose_resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
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 lixiaotong97/DSU, 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.

crop_image Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/utils/img.py
code served (permissive licence) · get_code("97259a9e1f81bfef")
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 ndarray, ndim 3, dtype family int, shape (6, 6, 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 numpy as np
from PIL import Image

# Create a small test image (height=10, width=15, 3 channels)
test_image = np.random.randint(0, 256, size=(10, 15, 3), dtype=np.uint8)

# Define a bounding box (left, upper, right, lower)
test_bbox = (2, 3, 8, 9)

ARGS = {
    "image": test_image,
    "bbox": test_bbox,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (6, 6, 3) — shape (6, 6, 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
euclidean_to_homogeneous Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/utils/multiview.py
code served (permissive licence) · get_code("41a9f998b3e64792")
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 ndarray, ndim 2, dtype family float, shape (2, 5) 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 numpy as np
import torch

torch.manual_seed(0)

# Test with numpy array
numpy_points = np.array([
    [1.0, 2.0, 3.0, 4.0],
    [5.0, 6.0, 7.0, 8.0]
])

ARGS = {
    "points": numpy_points
}
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 ndarray, ndim 2, dtype family float, shape (2, 5) — shape (2, 5) 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
fig_to_array Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/utils/vis.py
code served (permissive licence) · get_code("92ebb319daf6e5c7")
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 ndarray, ndim 3, dtype family int, shape (480, 640, 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 numpy as np
import matplotlib.pyplot as plt
import matplotlib
matplotlib.use('Agg')

# Create a simple figure with a canvas and renderer
fig = plt.figure()
ax = fig.add_subplot(111)
ax.plot([1, 2, 3], [1, 2, 3])

ARGS = {
    'fig': fig
}
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 ndarray, ndim 3, dtype family int, shape (480, 640, 4) — shape (480, 640, 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
get_rotation_matrix Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/utils/volumetric.py
code served (permissive licence) · get_code("3d898c27df7d558a")
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 ndarray, ndim 2, dtype family float, shape (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 numpy as np

# Construct arguments for get_rotation_matrix
# The function takes:
# - axis: a sequence/array representing the rotation axis
# - theta: a scalar angle in radians

ARGS = {
    "axis": np.array([1.0, 0.0, 0.0]),  # rotation axis (x-axis)
    "theta": np.pi / 4,  # rotation angle in radians (45 degrees)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (3, 3) — shape (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
get_square_bbox Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/utils/img.py
code served (permissive licence) · get_code("058c2ac5b4914ae8")
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, ndim 1, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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

# Analyze the function:
# - Takes a single parameter: bbox
# - bbox is a tuple of size 4 containing (left, upper, right, lower)
# - The function performs arithmetic operations on these values
# - Returns a tuple of size 4

# Create a valid bbox tuple
# Using distinct values to make the logic testable
bbox = (10, 20, 50, 60)  # left, upper, right, lower

ARGS = {
    "bbox": bbox
}
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 tuple, ndim 1, dtype family int — a tuple output has no array shape of its own; none is stated
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
homogeneous_to_euclidean Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/utils/multiview.py
code served (permissive licence) · get_code("f8bdb55803874cd3")
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 ndarray, 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 numpy as np
import torch

torch.manual_seed(0)

# Test with numpy array: N=2 homogeneous points of dimension M=3
# Homogeneous points have shape (N, M+1) = (2, 4)
numpy_points = np.array([
    [1.0, 2.0, 3.0, 2.0],
    [4.0, 5.0, 6.0, 4.0]
])

ARGS = {
    "points": numpy_points
}
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 ndarray, 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
integrate_tensor_2d Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/utils/op.py
code served (permissive licence) · get_code("1746cfe037b9bddc")
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
import torch.nn as nn

torch.manual_seed(0)

# Create a small heatmap tensor
# Shape: (batch_size=2, n_heatmaps=3, h=4, w=5)
heatmaps = torch.randn(2, 3, 4, 5)

ARGS = {
    "heatmaps": heatmaps,
    "softmax": 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 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
integrate_tensor_3d Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/utils/op.py
code served (permissive licence) · get_code("3438dea94010a241")
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
import torch.nn as nn

torch.manual_seed(0)

# Create a small 5D tensor with shape (batch_size, n_volumes, x_size, y_size, z_size)
# Using distinct sizes: batch=2, n_volumes=3, x=4, y=5, z=6
volumes = torch.randn(2, 3, 4, 5, 6)

ARGS = {
    "volumes": volumes,
    "softmax": 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 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
integrate_tensor_3d_with_coordinates Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/utils/op.py
code served (permissive licence) · get_code("200b87aeadd93f7a")
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
import torch.nn as nn

torch.manual_seed(0)

# Create small tensors with distinct dimensions for clarity
batch_size = 2
n_volumes = 3
x_size = 4
y_size = 5
z_size = 6
coord_channels = 7

# volumes: (batch_size, n_volumes, x_size, y_size, z_size)
volumes = torch.randn(batch_size, n_volumes, x_size, y_size, z_size)

# coord_volumes: (batch_size, x_size, y_size, z_size, coord_channels)
# This tensor is used in einsum: 'bxyzc' where c is coord_channels
coord_volumes = torch.randn(batch_size, x_size, y_size, z_size, coord_channels)

ARGS = {
    'volumes': volumes,
    'coord_volumes': coord_volumes,
    'softmax': 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 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
make_collate_fn Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/datasets/utils.py
code served (permissive licence) · get_code("401a09672d24d91d")
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 function. 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

# Set seed for reproducibility
np.random.seed(0)

# Create sample items that match the expected structure
def create_sample_item(n_views=15, n_keypoints=17, img_height=64, img_width=64):
    """Create a single item matching the expected dict structure"""
    item = {
        'images': [np.random.rand(img_height, img_width, 3).astype(np.float32) for _ in range(n_views)],
        'detections': [np.random.rand(n_keypoints, 3).astype(np.float32) for _ in range(n_views)],
        'cameras': [{'intrinsics': np.eye(3), 'extrinsics': np.eye(4)} for _ in range(n_views)],
        'keypoints_3d': np.random.rand(n_keypoints, 3).astype(np.float32),
        'indexes': np.arange(n_keypoints),
        'pred_keypoints_3d': np.random.rand(n_keypoints, 3).astype(np.float32),
    }
    return item

# Create a batch of items
batch_items = [
    create_sample_item(n_views=15, n_keypoints=17),
    create_sample_item(n_views=15, n_keypoints=17),
]

# Define arguments for make_collate_fn
ARGS = {
    'randomize_n_views': True,
    'min_n_views': 10,
    'max_n_views': 31,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
project_3d_points_to_image_plane_without_distortion Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/utils/multiview.py
code served (permissive licence) · get_code("5d25c0684ed04e72")
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, 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 numpy as np
import torch

torch.manual_seed(0)

# Create a projection matrix of shape (3, 4)
proj_matrix = torch.randn(3, 4)

# Create 3D points of shape (N, 3) where N=2
points_3d = torch.randn(2, 3)

# Convert back to euclidean is a boolean
convert_back_to_euclidean = True

ARGS = {
    'proj_matrix': proj_matrix,
    'points_3d': points_3d,
    'convert_back_to_euclidean': convert_back_to_euclidean
}
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 Tensor, ndim 2, dtype family float, shape (2, 2) — shape (2, 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
resize_image Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/utils/img.py
code served (permissive licence) · get_code("3658ef58769f24d4")
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 ndarray, ndim 3, dtype family int, shape (3, 5, 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 cv2
import numpy as np

# Create a sample image as a numpy array (height=4, width=6, channels=3)
image = np.random.randint(0, 256, size=(4, 6, 3), dtype=np.uint8)

# Define target shape (height=3, width=5)
shape = (3, 5)

ARGS = {
    "image": image,
    "shape": shape,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (3, 5, 3) — shape (3, 5, 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
rotate_coord_volume Ran
ran on a synthesized input
karfly/learnable-triangulation-pytorch/mvn/utils/volumetric.py
code served (permissive licence) · get_code("621b296fbf0065a0")
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 5, dtype family float, shape (2, 4, 5, 6, 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
import numpy as np

torch.manual_seed(0)

# Create a small coordinate volume tensor
# Shape: (batch, height, width, depth, 3) - representing 3D coordinates
# Using distinct sizes: 2, 4, 5, 6 for each dimension
coord_volume = torch.randn(2, 4, 5, 6, 3, dtype=torch.float32)

# Define rotation angle in radians
theta = np.pi / 4  # 45 degrees

# Define rotation axis (normalized direction)
axis = [1, 0, 0]  # Rotate around x-axis

ARGS = {
    "coord_volume": coord_volume,
    "theta": theta,
    "axis": axis
}
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 Tensor, ndim 5, dtype family float, shape (2, 4, 5, 6, 3) — shape (2, 4, 5, 6, 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
get_pose_net Not yet run
unverified (harvested, no recorded run)
karfly/learnable-triangulation-pytorch/mvn/models/pose_resnet.py
code served (permissive licence) · get_code("4b5bb331e9336255")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 16 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
conv3x3 686 other papers
119 dated earlier, 12 the same month, 555 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here

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

We present two novel solutions for multi-view 3D human pose estimation based on new learnable triangulation methods that combine 3D information from multiple 2D views. The first (baseline) solution is a basic differentiable algebraic triangulation with an addition of confidence weights estimated from the input images. The second solution is based on a novel method of volumetric aggregation from intermediate 2D backbone feature maps. The aggregated volume is then refined via 3D convolutions that produce final 3D joint heatmaps and allow modelling a human pose prior. Crucially, both approaches are end-to-end differentiable, which allows us to directly optimize the target metric. We demonstrate transferability of the solutions across datasets and considerably improve the multi-view state of the art on the Human3.6M dataset. Video demonstration, annotations and additional materials will be posted on our project page (https://saic-violet.github.io/learnable-triangulation).

For agents

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

get_harvested_code_for_paper("1905.05754")
get_code_for_paper("1905.05754")
have("1905.05754")

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

curl https://syntology.ai/api/ran/1905.05754.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.05754.svg)](https://syntology.ai/paper/1905.05754)

Connect an agent — have() is free.