SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.11207 · 2021

Fully Convolutional Line Parsing

arXiv · PDF · Open in the Atlas

Code that ran

11 of 19 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 4 have no contract verdict; 7 failures of our instrument; 8 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/2104.11207.json · badge: /api/ran/2104.11207.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
Delay-Xili/F-Clip canonical (classifier label)
classifier basis: census
7 ran · 2 no recorded run
PINTO0309/PINTO_model_zoo community (classifier label)
classifier basis not recorded on the link
4 ran · 6 no recorded run
FunctionStatusWhere it lives
ap Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Delay-Xili/F-Clip/FClip/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
collate Ran
ran; our contract draft was wrong, not the code
Delay-Xili/F-Clip/FClip/datasets.py
code served (permissive licence) · get_code("624365544af5330a")
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
from torch.utils.data.dataloader import default_collate

torch.manual_seed(0)

# The collate function expects a batch where each element is a tuple of (tensor, label, tensor)
# It uses default_collate on b[0] and b[2], and keeps b[1] as a list

batch = [
    (torch.randn(2, 4), "label_0", torch.randn(3, 4)),
    (torch.randn(2, 4), "label_1", torch.randn(3, 4)),
]

ARGS = {
    "batch": batch
}
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
conv3x3 Ran
ran; our contract draft was wrong, not the code
Delay-Xili/F-Clip/FClip/models/pose_hrnet.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.

get_graph_def_from_file Ran
ran on a synthesized input
PINTO0309/PINTO_model_zoo/007_mobilenetv2-poseestimation/01_float32/02_pb_to_saved_model.py
code served (permissive licence) · get_code("0e829dba312cea5f")
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 GraphDef. 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 tensorflow as tf
import tempfile
import os

# Create a minimal valid TensorFlow graph and save it to a temporary file
def create_minimal_graph_file():
    # Create a simple graph with one operation
    tf.compat.v1.reset_default_graph()
    with tf.compat.v1.Graph().as_default():
        # Add a simple constant operation
        x = tf.constant(1.0, name='constant_op')
        
        # Get the graph definition
        graph_def = tf.compat.v1.get_default_graph().as_graph_def()
    
    # Write to a temporary file
    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.pb')
    temp_file.write(graph_def.SerializeToString())
    temp_file.close()
    
    return temp_file.name

# Create the graph file
graph_filepath = create_minimal_graph_file()

# Define arguments for the function
ARGS = {
    'graph_filepath': graph_filepath
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type GraphDef — a GraphDef output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a GraphDef 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
get_model Ran
ran on a synthesized input
PINTO0309/PINTO_model_zoo/071_Noise2Noise/model.py
code served (permissive licence) · get_code("62283db35d874061")
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 Functional. 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 tensorflow as tf
import numpy as np

ARGS = {
    'height': 64,
    'width': 64,
    'model_name': 'srresnet'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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
get_noise_model Ran
ran on a synthesized input
PINTO0309/PINTO_model_zoo/071_Noise2Noise/noise_model.py
code served (permissive licence) · get_code("843f6a8c8d2d4cf8")
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 string
import random
import numpy as np
import cv2

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

# Test different noise types
ARGS = {
    'noise_type': 'gaussian,0,50'
}

# Verify the function works with this argument
def get_noise_model(noise_type='gaussian,0,50'):
    tokens = noise_type.split(sep=',')
    if tokens[0] == 'gaussian':
        min_stddev = int(tokens[1])
        max_stddev = int(tokens[2])

        def gaussian_noise(img):
            noise_img = img.astype(np.float)
            stddev = np.random.uniform(min_stddev, max_stddev)
            noise = np.random.randn(*img.shape) * stddev
            noise_img += noise
            noise_img = np.clip(noise_img, 0, 255).astype(np.uint8)
            return noise_img
        return gaussian_noise
    elif tokens[0] == 'clean':
        return lambda img: img
    elif tokens[0] == 'text':
        min_occupancy = int(tokens[1])
        max_occupancy = int(tokens[2])

        def add_text(img):
            img = img.copy()
            h, w, _ = img.shape
            font = cv2.FONT_HERSHEY_SIMPLEX
            img_for_cnt = np.zeros((h, w), np.uint8)
            occupancy = np.random.uniform(min_occupancy, max_occupancy)
            while True:
                n = random.randint(5, 10)
                random_str = ''.join([random.choice(string.ascii_letters + string.digits) for i in range(n)])
                font_scale = np.random.uniform(0.5, 1)
                thickness = random.randint(1, 3)
                (fw, fh), baseline = cv2.getTextSize(random_str, font, font_scale, thickness)
                x = random.randint(0, max(0, w - 1 - fw))
                y = random.randint(fh, h - 1 - baseline)
                color = (random.randint(0, 255), random.randint(0, 255), random.randint(0, 255))
                cv2.putText(img, random_str, (x, y), font, font_scale, color, thickness)
                cv2.putText(img_for_cnt, random_str, (x, y), font, font_scale, 255, thickness)
                if (img_for_cnt > 0).sum() > h * w * occupancy / 100:
                    break
            return img
        return add_text
    elif tokens[0] == 'impulse':
        min_occupancy = int(tokens[1])
        max_occupancy = int(tokens[2])

        def add_impulse_noise(img):
            occupancy = np.random.uniform(min_occupancy, max_occupancy)
            mask = np.random.binomial(size=img.shape, n=1, p=occupancy / 100)
            noise = np.random.randint(256, size=img.shape)
            img = img * (1 - mask) + noise * mask
            return img.astype(np.uint8)
        return add_impulse_noise
    else:
        raise ValueError("noise_type should be 'gaussian', 'clean', 'text', or 'impulse'")

ARGS = {
    'noise_type': 'gaussian,0,50'
}
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 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
init_lr_scheduler Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Delay-Xili/F-Clip/FClip/lr_schedulers.py
code served (permissive licence) · get_code("cf7293640b3170a1")
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 MultiStepLR. 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
from torch.optim import SGD

torch.manual_seed(0)

# Create a minimal model
class SimpleModel(nn.Module):
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Instantiate model and optimizer
model = SimpleModel()
optimizer = SGD(model.parameters(), lr=0.1)

# Define ARGS dict with all parameters for init_lr_scheduler
ARGS = {
    'optimizer': optimizer,
    'lr_scheduler': 'multi_step',
    'stepsize': [20, 40],
    'gamma': 0.1,
    'max_epoch': 240,
    'eta_min': 0,
    'warmUp_epoch': 5,
    'last_epoch': -1
}
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 MultiStepLR — a MultiStepLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a MultiStepLR 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
non_maximum_suppression Ran
ran; our contract draft was wrong, not the code
Delay-Xili/F-Clip/FClip/nms.py
code served (permissive licence) · get_code("a58f56d0f6bd4d2a")
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 4, dtype family float, shape (2, 1, 4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create a small 4D tensor (batch_size=2, channels=1, height=4, width=3)
# Using values that will create some local maxima for non-maximum suppression
a = torch.tensor([
    [[[1.0, 2.0, 1.5],
      [3.0, 5.0, 2.0],
      [2.0, 4.0, 1.0],
      [1.0, 1.5, 0.5]]],
    [[[0.5, 1.0, 0.8],
      [2.0, 3.5, 1.5],
      [1.5, 2.5, 0.9],
      [0.7, 1.2, 0.3]]]
])

ARGS = {
    "a": a,
    "delta": 0.1,
    "kernel": 3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 1, 4, 3) — shape (2, 1, 4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
optimizing_hardswish_for_edgetpu Ran
ran on a synthesized input
PINTO0309/PINTO_model_zoo/082_MediaPipe_Meet_Segmentation/01_segm_lite_v509_tflite_to_pb_saved_model.py
code served (permissive licence) · get_code("ba2e5d92a859bd80")
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 SymbolicTensor. 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 tensorflow.compat.v1 as tf
import numpy as np

tf.disable_v2_behavior()

# Create a small input tensor
input_tensor = tf.constant(
    np.random.randn(2, 4).astype(np.float32),
    dtype=tf.float32
)

ARGS = {
    "input_op": input_tensor,
    "name": "hardswish_op"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type SymbolicTensor — a SymbolicTensor 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
structure_nms Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Delay-Xili/F-Clip/FClip/nms.py
code served (permissive licence) · get_code("4498fbf267a33954")
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

# Construct valid arguments for structure_nms
# The function expects:
# - lines: a 2D array of shape (n, 2, 2) representing line segments
# - scores: a 1D array of shape (n,) representing confidence scores
# - threshold: a float threshold for NMS
# - delta: a float for scaling dropped detections

# Create sample lines: shape (4, 2, 2) - 4 line segments, each defined by 2 points with 2 coordinates
lines = np.array([
    [[0.0, 0.0], [1.0, 1.0]],
    [[0.1, 0.1], [1.1, 1.1]],
    [[5.0, 5.0], [6.0, 6.0]],
    [[10.0, 10.0], [11.0, 11.0]]
], dtype=np.float32)

# Create sample scores: shape (4,) - one score per line
scores = np.array([0.9, 0.8, 0.7, 0.6], dtype=np.float32)

# Set threshold for NMS
threshold = 2.0

# Set delta for scaling
delta = 0.5

ARGS = {
    "lines": lines,
    "scores": scores,
    "threshold": threshold,
    "delta": delta
}
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 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
structure_nms_torch Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Delay-Xili/F-Clip/FClip/nms.py
code served (permissive licence) · get_code("a218e03e98eafb64")
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

torch.manual_seed(0)

# lines: tensor of shape (N, 2, 2) representing N line segments with 2 endpoints of 2D coordinates
# scores: tensor of shape (N,) representing scores for each line
lines = torch.tensor([
    [[0.0, 0.0], [1.0, 1.0]],
    [[0.1, 0.1], [1.1, 1.1]],
], dtype=torch.float32)

scores = torch.tensor([0.9, 0.8], dtype=torch.float32)

threshold = 2

ARGS = {
    "lines": lines,
    "scores": scores,
    "threshold": threshold
}
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
APJ Not yet run
unverified (harvested, no recorded run)
Delay-Xili/F-Clip/FClip/metric.py
code served (permissive licence) · get_code("02b2ffeb173ebb15")
How it ran

no invocation recorded.

PSNR Not yet run
unverified (harvested, no recorded run)
PINTO0309/PINTO_model_zoo/071_Noise2Noise/model.py
code served (permissive licence) · get_code("8b86297f01fc1975")
How it ran

no invocation recorded.

get_graph_def_from_file Not yet run
unverified (harvested, no recorded run)
PINTO0309/PINTO_model_zoo/007_mobilenetv2-poseestimation/dm050_224/01_freeze_the_saved_model.py
code served (permissive licence) · get_code("2941f56720d60ef7")
How it ran

no invocation recorded.

mAPJ Not yet run
unverified (harvested, no recorded run)
Delay-Xili/F-Clip/FClip/metric.py
code served (permissive licence) · get_code("6d6cfc939498bd6b")
How it ran

no invocation recorded.

make_graph Not yet run
unverified (harvested, no recorded run)
PINTO0309/PINTO_model_zoo/082_MediaPipe_Meet_Segmentation/01_segm_lite_v509_tflite_to_pb_saved_model.py
code served (permissive licence) · get_code("b9b75736ab77054a")
How it ran

no invocation recorded.

make_graph Not yet run
unverified (harvested, no recorded run)
PINTO0309/PINTO_model_zoo/082_MediaPipe_Meet_Segmentation/02_segm_full_v679_tflite_to_pb_saved_model.py
code served (permissive licence) · get_code("370b7fb5b138c7d6")
How it ran

no invocation recorded.

make_graph Not yet run
unverified (harvested, no recorded run)
PINTO0309/PINTO_model_zoo/082_MediaPipe_Meet_Segmentation/03_segm_lite_v681_tflite_to_pb_saved_model.py
code served (permissive licence) · get_code("2b31112f5b169d48")
How it ran

no invocation recorded.

tf_log10 Not yet run
unverified (harvested, no recorded run)
PINTO0309/PINTO_model_zoo/071_Noise2Noise/model.py
code served (permissive licence) · get_code("eb1a712b7ccc8e72")
How it ran

no invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 1 later) and 15 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
285 dated earlier, 19 the same month, 376 later, 6 same year, order not determinable · 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
ap 2 other papers
2 dated earlier
1905.03246 (2019-05)
End-to-End Wireframe Parsing
1905.07482 (2019-05)
Learning to Reconstruct 3D Manhattan Wireframes from a Single Image
APJ 1 other paper
1 dated earlier
1905.03246 (2019-05)
End-to-End Wireframe Parsing
collate 1 other paper
1 dated earlier
1905.03246 (2019-05)
End-to-End Wireframe 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

We present a one-stage Fully Convolutional Line Parsing network (F-Clip) that detects line segments from images. The proposed network is very simple and flexible with variations that gracefully trade off between speed and accuracy for different applications. F-Clip detects line segments in an end-to-end fashion by predicting each line's center position, length, and angle. We further customize the design of convolution kernels of our fully convolutional network to effectively exploit the statistical priors of the distribution of line angles in real image datasets. We conduct extensive experiments and show that our method achieves a significantly better trade-off between efficiency and accuracy, resulting in a real-time line detector at up to 73 FPS on a single GPU. Such inference speed makes our method readily applicable to real-time tasks without compromising any accuracy of previous methods. Moreover, when equipped with a performance-improving backbone network, F-Clip is able to significantly outperform all state-of-the-art line detectors on accuracy at a similar or even higher frame rate. In other word, under same inference speed, F-Clip always achieving best accuracy compare with other methods. Source code https://github.com/Delay-Xili/F-Clip.

For agents

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

get_harvested_code_for_paper("2104.11207")
get_code_for_paper("2104.11207")
have("2104.11207")

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

curl https://syntology.ai/api/ran/2104.11207.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.11207.svg)](https://syntology.ai/paper/2104.11207)

Connect an agent — have() is free.