SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.07482 · 2019

Learning to Reconstruct 3D Manhattan Wireframes from a Single Image

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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; 3 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1905.07482.json · badge: /api/ran/1905.07482.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
zhou13/shapeunity canonical (classifier label)
classifier basis: classifier_2025
4 ran · 1 no recorded run
FunctionStatusWhere it lives
ap Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhou13/shapeunity/eval_2d3d_metric.py
code served (permissive licence) · get_code("6cc7fd04d6d9a593")
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 float64, 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 numpy as np

# The function `ap` takes two parameters: tp and fp
# Both should be numpy arrays based on how they're used:
# - They're concatenated with np.concatenate
# - They're indexed with np.where
# - They support arithmetic operations (tp / (tp + fp))

# Create small numpy arrays for tp and fp
tp = np.array([0.1, 0.3, 0.5, 0.7, 0.9])
fp = np.array([0.05, 0.1, 0.15, 0.2, 0.25])

ARGS = {
    "tp": tp,
    "fp": fp
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 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
filter_heatmap Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhou13/shapeunity/vectorize_u3d.py
code served (permissive licence) · get_code("0129eeab74419004")
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 list, 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 numpy as np

# Create a small heatmap (2D array)
h = np.array([
    [0.1, 0.8, 0.3],
    [0.9, 0.2, 0.7]
], dtype=np.float32)

# Set threshold
h_threshold = 0.5

# Create offset array with shape [2, 2, 3] (2 channels, 2 rows, 3 cols)
offset = np.array([
    [[0.1, 0.2, 0.3], [0.4, 0.5, 0.6]],
    [[0.05, 0.15, 0.25], [0.35, 0.45, 0.55]]
], dtype=np.float32)

ARGS = {
    "h": h,
    "h_threshold": h_threshold,
    "offset": offset
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 2, dtype family float — a list 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
line_color Ran
ran, violated the contract we drafted
zhou13/shapeunity/vectorize_u3d.py
code served (permissive licence) · get_code("aa219e4d8e0533f7")
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 tuple, ndim 1, 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 matplotlib as mpl
import matplotlib.pyplot as plt
import numpy as np

cmap = plt.get_cmap('jet')
norm = mpl.colors.Normalize(vmin=0.6, vmax=1.1)
sm = plt.cm.ScalarMappable(cmap=cmap, norm=norm)

def line_color(x):
    return sm.to_rgba(x)

# The function takes a single parameter x which is passed to sm.to_rgba()
# to_rgba expects a scalar or array-like value in the normalized range
# We'll provide a scalar float value within the normalization range [0.6, 1.1]

ARGS = {
    'x': 0.85
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
matplotlib, numpy — 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 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
project Ran
ran; our contract draft was wrong, not the code
zhou13/shapeunity/vectorize_u3d.py
code served (permissive licence) · get_code("b406c63e7f1d3eee")
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 tuple, ndim 1, 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

torch.manual_seed(0)

# The function project takes three parameters: c, a, b
# Each is used as a 2-element sequence with indexing [0] and [1]
# They represent points in 2D space

c = (1.5, 2.5)
a = (0.0, 0.0)
b = (4.0, 3.0)

ARGS = {
    "c": c,
    "a": a,
    "b": b
}
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 tuple, ndim 1, 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
msTPFP_hit Not yet run
unverified (harvested, no recorded run)
zhou13/shapeunity/eval_2d3d_metric.py
code served (permissive licence) · get_code("63b5425d2774705a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 1 the same month, 1 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
ap 2 other papers
1 the same month, 1 later
1905.03246 (2019-05)
End-to-End Wireframe Parsing
2104.11207 (2021-04)
Fully Convolutional Line Parsing

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

In this paper, we propose a method to obtain a compact and accurate 3D wireframe representation from a single image by effectively exploiting global structural regularities. Our method trains a convolutional neural network to simultaneously detect salient junctions and straight lines, as well as predict their 3D depth and vanishing points. Compared with the state-of-the-art learning-based wireframe detection methods, our network is simpler and more unified, leading to better 2D wireframe detection. With global structural priors from parallelism, our method further reconstructs a full 3D wireframe model, a compact vector representation suitable for a variety of high-level vision tasks such as AR and CAD. We conduct extensive evaluations on a large synthetic dataset of urban scenes as well as real images. Our code and datasets have been made public at https://github.com/zhou13/shapeunity.

For agents

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

get_harvested_code_for_paper("1905.07482")
get_code_for_paper("1905.07482")
have("1905.07482")

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

curl https://syntology.ai/api/ran/1905.07482.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.07482.svg)](https://syntology.ai/paper/1905.07482)

Connect an agent — have() is free.