SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.08586 · CVPR · 2022

Deep vanishing point detection: Geometric priors make dataset variations vanish

Jan Van Gemert, Silvia Pintea, Yancong Lin, Ruben Wiersma, Klaus Hildebrandt, Elmar Eisemann

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, 1 violated it and 13 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/2203.08586.json · badge: /api/ran/2203.08586.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
yanconglin/vanishingpoint_houghtransform_gaussiansphere canonical (classifier label)
classifier basis not recorded on the link
16 ran · 1 no recorded run
FunctionStatusWhere it lives
AA Ran
ran on a synthesized input
yanconglin/vanishingpoint_houghtransform_gaussiansphere/eval_manhattan.py
code served (permissive licence) · get_code("e9cd554cae456073")
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 float64, ndim 0, dtype family float; 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 numpy as np

# Analyzing the function AA:
# - x: numpy array, used with np.searchsorted and np.concatenate
# - y: numpy array, used with np.concatenate and arithmetic operations
# - threshold: scalar value, used with np.searchsorted and division
# The function performs a numerical integration-like operation

# Create small numpy arrays with distinct sizes
x = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
y = np.array([0.5, 1.0, 1.5, 2.0, 2.5])
threshold = 3.5

ARGS = {
    "x": x,
    "y": y,
    "threshold": threshold
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
MLP Ran
ran on a synthesized input
yanconglin/vanishingpoint_houghtransform_gaussiansphere/vpd/models/dgcn.py
code served (permissive licence) · get_code("5c8d2e6ae1329291")
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 = {
    'channels': [64, 128, 256, 512],
    'num_points': 2048,
    'channel_last': True,
    'bias': 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 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 2 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
calc_auc Ran
ran on a synthesized input
yanconglin/vanishingpoint_houghtransform_gaussiansphere/cluster_nyu.py
code served (permissive licence) · get_code("52bdb37b8c80883e")
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 numpy as np

# The function takes an error_array and optional cutoff parameter
# error_array should be a numpy array that can be squeezed and sorted
# cutoff is a float threshold value

# Create a small error array with some values
error_array = np.array([0.1, 0.15, 0.2, 0.3, 0.35, 0.4, 0.5])

# Define ARGS dict with all parameters
ARGS = {
    "error_array": error_array,
    "cutoff": 0.25
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
catersian_to_sphere Ran
ran on a synthesized input
yanconglin/vanishingpoint_houghtransform_gaussiansphere/parameterization.py
code served (permissive licence) · get_code("deee09d09b6a5086")
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, 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

# Create a small xyz array with cartesian coordinates
# The function expects shape (num_points, 3) based on indexing xyz[:, 0], xyz[:, 1]
xyz = np.array([
    [0.6, 0.5, 0.3],
    [0.8, 0.2, 0.4],
], dtype=np.float32)

ARGS = {
    "xyz": xyz
}
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 (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
compute_error Ran
ran on a synthesized input
yanconglin/vanishingpoint_houghtransform_gaussiansphere/eval_manhattan.py
code served (permissive licence) · get_code("6125c3a4aaf2b8b3")
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 1, dtype family float, shape (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

# Construct small valid arguments for compute_error
# The function expects:
# - vps_pd: predicted vanishing points (shape: N x D)
# - vps_gt: ground truth vanishing points (shape: M x D)
# Both should be 2D numpy arrays that can be matrix multiplied

# Create small arrays with distinct dimensions for clarity
# vps_gt: 2 ground truth points, 3 dimensions each
vps_gt = np.array([
    [1.0, 0.0, 0.0],
    [0.0, 1.0, 0.0]
], dtype=np.float32)

# vps_pd: 4 predicted points, 3 dimensions each
vps_pd = np.array([
    [0.9, 0.1, 0.0],
    [0.1, 0.95, 0.0],
    [0.0, 0.0, 1.0],
    [0.5, 0.5, 0.0]
], dtype=np.float32)

ARGS = {
    'vps_pd': vps_pd,
    'vps_gt': vps_gt
}
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 1, dtype family float, shape (2,) — shape (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
cos_cdis Ran
ran on a synthesized input
yanconglin/vanishingpoint_houghtransform_gaussiansphere/parameterization.py
code served (permissive licence) · get_code("cb8ab53d2a62789f")
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 scipy.spatial.distance as scipy_spatial_dist

np.random.seed(0)

# Create small sample data for x and y
# x: shape (2, 4) - 2 samples, 4 dimensions
# y: shape (3, 4) - 3 samples, 4 dimensions
x = np.random.randn(2, 4).astype(np.float32)
y = np.random.randn(3, 4).astype(np.float32)

# semi_sphere: boolean flag
semi_sphere = False

ARGS = {
    'x': x,
    'y': y,
    'semi_sphere': semi_sphere
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
gold_spiral_sampling_patch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yanconglin/vanishingpoint_houghtransform_gaussiansphere/misc/find-radius.py
code served (permissive licence) · get_code("08fa3af6222de022")
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 (10, 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 math

# Analyze the function signature and usage:
# - v: used with indexing v[0], v[1], v[2], and v[:, None], so needs to be a 1D numpy array of length 3
# - alpha: used in math.cos(alpha), so a scalar float
# - num_pts: used in range/indexing operations, so an integer

# Create the arguments
v = np.array([1.0, 0.5, 0.3])  # 3D direction vector
alpha = math.pi / 4  # angle in radians
num_pts = 10  # number of points to sample

ARGS = {
    "v": v,
    "alpha": alpha,
    "num_pts": num_pts
}
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 (10, 3) — shape (10, 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
line_vp_distances Ran
ran on a synthesized input
yanconglin/vanishingpoint_houghtransform_gaussiansphere/dataset/yud_process.py
code served (permissive licence) · get_code("4ec6861f58a7539c")
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

# Analyze the function:
# - lines: shape (n_lines, 12) - accessed at indices [li, 6:9] and [li, 9:12]
# - vps: shape (n_vps, 3) - accessed at indices [vi, :] and [vi, 0:2]
# The function computes distances between line directions and vanishing points

# Create small test data
n_lines = 2
n_vps = 3

# lines: each row has 12 elements
# - indices 6:9 are the line direction vector
# - indices 9:12 are the centroid
lines = np.random.randn(n_lines, 12).astype(np.float32)
# Normalize the line direction vectors to be valid
lines[:, 6:9] /= np.linalg.norm(lines[:, 6:9], axis=1, keepdims=True)

# vps: each row is a 3D vanishing point
vps = np.random.randn(n_vps, 3).astype(np.float32)
# Normalize vanishing points
vps /= np.linalg.norm(vps, axis=1, keepdims=True)

ARGS = {
    "lines": lines,
    "vps": vps,
}
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 (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
make_conv1d_block Ran
ran on a synthesized input
yanconglin/vanishingpoint_houghtransform_gaussiansphere/vpd/models/convs.py
code served (permissive licence) · get_code("20101849e7104ea6")
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 = {
    "in_channels": 3,
    "out_channels": 16,
    "kernel_size": 3,
    "stride": 1,
    "padding": 1,
    "dilation": 1,
    "groups": 1,
    "bias": 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_conv2d_block Ran
ran on a synthesized input
yanconglin/vanishingpoint_houghtransform_gaussiansphere/vpd/models/convs.py
code served (permissive licence) · get_code("d977e87d61e39ae2")
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 = {
    "in_channels": 3,
    "out_channels": 16,
    "kernel_size": 3,
    "stride": 1,
    "padding": 1,
    "dilation": 1,
    "groups": 1,
    "bias": 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
orth Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yanconglin/vanishingpoint_houghtransform_gaussiansphere/misc/find-radius.py
code served (permissive licence) · get_code("b6cf865210ac7f8c")
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 1, dtype family float, shape (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

# The function 'orth' takes a parameter 'v' which should be a sequence/array-like
# object with exactly 3 elements (x, y, z) based on the unpacking: x, y, z = v
# The function computes an orthogonal vector to v using numpy operations

v = np.array([1.0, 2.0, 3.0])

ARGS = {
    "v": v
}
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 1, dtype family float, shape (3,) — shape (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
rgb2gray Ran
ran, violated the contract we drafted
yanconglin/vanishingpoint_houghtransform_gaussiansphere/dataset/nyu_process.py
code served (permissive licence) · get_code("eb7801586aa2560a")
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, 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

# Create a small RGB image array
# Shape: (height, width, channels) where channels includes RGB + potentially extra
# Using shape (2, 4, 3) for a 2x4 RGB image
rgb_image = np.random.rand(2, 4, 3).astype(np.float32)

ARGS = {
    "rgb": rgb_image
}
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 (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
sphere_to_catesian Ran
ran on a synthesized input
yanconglin/vanishingpoint_houghtransform_gaussiansphere/parameterization.py
code served (permissive licence) · get_code("b54f63482cf3c0fc")
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

torch_manual_seed = None  # Not needed for this function

# Create sample spherical angles
# angles should be a 2D array where each row contains [theta, phi]
# theta: azimuthal angle (0 to 2π)
# phi: polar angle (0 to π)
angles = np.array([
    [np.pi / 4, np.pi / 6],      # First point
    [np.pi / 3, np.pi / 4],      # Second point
])

ARGS = {
    "angles": angles
}
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 (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
to_pixel Ran
ran on a synthesized input
yanconglin/vanishingpoint_houghtransform_gaussiansphere/dataset/nyu_process.py
code served (permissive licence) · get_code("ca6ab07fef75b6fb")
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 2, dtype family float; 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

torch.manual_seed(0)

# vpts is indexed with [:, 0], [:, 1], [:, 2], so it needs to be a 2D array/tensor
# with at least 3 columns. Let's make it shape (2, 3) - 2 points with x, y, z coordinates
vpts = torch.tensor([
    [1.0, 2.0, 5.0],
    [3.0, -1.0, 8.0]
], dtype=torch.float32)

ARGS = {
    "vpts": vpts,
    "focal_length": 1.0,
    "h": 480,
    "w": 640
}
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 2, dtype family float — 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
topk_orthogonal_vps Ran
ran on a synthesized input
yanconglin/vanishingpoint_houghtransform_gaussiansphere/eval_manhattan.py
code served (permissive licence) · get_code("b6054b5cbf636a16")
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 numpy as np
import scipy.spatial.distance as scipy_spatial_dist

np.random.seed(0)

# Create sample data
# scores: 1D array of confidence scores
scores = np.array([0.9, 0.7, 0.6, 0.5, 0.4])

# xyz: 2D array of 3D unit vectors (vanishing points)
# Shape: (num_candidates, 3)
xyz = np.array([
    [1.0, 0.0, 0.0],
    [0.0, 1.0, 0.0],
    [0.707, 0.707, 0.0],
    [0.577, 0.577, 0.577],
    [0.0, 0.0, 1.0]
])

# Normalize to unit vectors for cosine distance
xyz = xyz / np.linalg.norm(xyz, axis=1, keepdims=True)

num_vps = 3

ARGS = {
    "scores": scores,
    "xyz": xyz,
    "num_vps": num_vps,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
vps_clustering Ran
ran on a synthesized input
yanconglin/vanishingpoint_houghtransform_gaussiansphere/cluster_nyu.py
code served (permissive licence) · get_code("0afe3afc1f40f8df")
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 numpy as np
import scipy.sparse
from sklearn.cluster import DBSCAN

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

# Create small test data
# vps_prob: probability scores for vanishing points (1D array)
vps_prob = np.array([0.1, 0.2, 0.95, 0.3, 0.15, 0.92, 0.05, 0.88, 0.12, 0.25])

# xyz: 3D coordinates on unit sphere (N x 3)
# Create normalized random vectors to represent points on sphere
xyz_raw = np.random.randn(10, 3)
xyz = xyz_raw / np.linalg.norm(xyz_raw, axis=1, keepdims=True)

# threshold: probability threshold for filtering
threshold = 0.5

ARGS = {
    'vps_prob': vps_prob,
    'xyz': xyz,
    'threshold': threshold
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy, sklearn — 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
single_eval_nyu Not yet run
unverified (harvested, no recorded run)
yanconglin/vanishingpoint_houghtransform_gaussiansphere/cluster_nyu.py
code served (permissive licence) · get_code("20597725bc4f8ab6")
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, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 1 later) and 14 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
rgb2gray 4 other papers
3 dated earlier, 1 later
1909.08313 (2019-09)
Unsupervised Sketch-to-Photo Synthesis
2105.02047 (2021-05)
Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images
2109.15271 (2021-09)
TöRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis
and 1 more not named here
gold_spiral_sampling_patch 2 other papers
2 dated earlier
1910.06316 (2019-10)
NeurVPS: Neural Vanishing Point Scanning via Conic Convolution
2105.03211 (2021-05)
NeRD: Neural 3D Reflection Symmetry Detector
orth 2 other papers
2 dated earlier
1910.06316 (2019-10)
NeurVPS: Neural Vanishing Point Scanning via Conic Convolution
2105.03211 (2021-05)
NeRD: Neural 3D Reflection Symmetry Detector

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

Deep learning has improved vanishing point detection in images. Yet, deep networks require expensive annotated datasets trained on costly hardware and do not generalize to even slightly different domains, and minor problem variants. Here, we address these issues by injecting deep vanishing point detection networks with prior knowledge. This prior knowledge no longer needs to be learned from data, saving valuable annotation efforts and compute, unlocking realistic few-sample scenarios, and reducing the impact of domain changes. Moreover, the interpretability of the priors allows to adapt deep networks to minor problem variations such as switching between Manhattan and non-Manhattan worlds. We seamlessly incorporate two geometric priors: (i) Hough Transform -mapping image pixels to straight lines, and (ii) Gaussian sphere -mapping lines to great circles whose intersections denote vanishing points. Experimentally, we ablate our choices and show comparable accuracy to existing models in the large-data setting. We validate our model's improved data efficiency, robustness to domain changes, adaptability to non-Manhattan settings.

For agents

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

get_harvested_code_for_paper("2203.08586")
get_code_for_paper("2203.08586")
have("2203.08586")

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

curl https://syntology.ai/api/ran/2203.08586.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.08586.svg)](https://syntology.ai/paper/2203.08586)

Connect an agent — have() is free.