SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.15302 · CVPR · 2022

Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes

Dongkwon Jin, Chang-Su Kim, Wonhui Park, Seong-Gyun Jeong, Heeyeon Kwon

arXiv · PDF · Open in the Atlas

Code that ran

10 of 15 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 7 have no contract verdict; 3 failures of our instrument; 5 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/2203.15302.json · badge: /api/ran/2203.15302.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
dongkwonjin/Eigenlanes canonical (classifier label)
classifier basis not recorded on the link
10 ran · 5 no recorded run
FunctionStatusWhere it lives
args_to_config Ran
ran on a synthesized input
dongkwonjin/Eigenlanes/Modeling/culane/code/options/args.py
code served (permissive licence) · get_code("1218471fbf1d452b")
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 ConfigStandIn. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np
from argparse import Namespace

torch.manual_seed(0)

# Create a config object with required structure
class ConfigStandIn:
    def __init__(self):
        self.dir = {
            'dataset': '/default/dataset',
            'head_pre': '/default/head_pre',
            'pre0': 'path/to/--preprocessed data path/pre0',
            'pre1': 'path/to/--preprocessed data path/pre1',
            'pre2': 'path/to/--preprocessed data path/pre2',
            'pre3': 'path/to/--preprocessed data path/pre3',
            'pre4': 'path/to/--preprocessed data path/pre4',
            'weight_paper': '/default/weights'
        }
        self.do_eval_culane_official = False
        self.sampling_step1 = 5
        self.run_mode = 'train'

cfg = ConfigStandIn()

# Create args object with all required attributes
args = Namespace(
    dataset_dir='/custom/dataset',
    pre_dir='/custom/preprocessed',
    paper_weight_dir='/custom/weights/paper',
    run_mode='test_paper'
)

ARGS = {
    'cfg': cfg,
    'args': args
}
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 ConfigStandIn — a ConfigStandIn output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ConfigStandIn 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
call_culane_eval_custom Ran
ran; our contract draft was wrong, not the code
dongkwonjin/Eigenlanes/Modeling/culane/code/evaluation/eval_culane_official.py
code served (permissive licence) · get_code("5b1117c2c47c0666")
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 dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile
import shutil

# Create a temporary directory structure for the test
temp_dir = tempfile.mkdtemp()
data_dir = os.path.join(temp_dir, 'culane_data')
output_path = os.path.join(temp_dir, 'output')

# Create necessary directory structure
os.makedirs(os.path.join(data_dir, 'list', 'test_split'), exist_ok=True)
os.makedirs(output_path, exist_ok=True)

# Create test list files (empty files are sufficient for this setup)
list_files = [
    'test0_normal.txt',
    'test1_crowd.txt',
    'test2_hlight.txt',
    'test3_shadow.txt',
    'test4_noline.txt',
    'test5_arrow.txt',
    'test6_curve.txt',
    'test7_cross.txt',
    'test8_night.txt'
]

for list_file in list_files:
    list_path = os.path.join(data_dir, 'list', 'test_split', list_file)
    with open(list_path, 'w') as f:
        f.write('')

# Create mock output files with proper format for read_helper
output_txt_dir = os.path.join(output_path, 'txt')
os.makedirs(output_txt_dir, exist_ok=True)

output_files = [
    'out0_normal.txt',
    'out1_crowd.txt',
    'out2_hlight.txt',
    'out3_shadow.txt',
    'out4_noline.txt',
    'out5_arrow.txt',
    'out6_curve.txt',
    'out7_cross.txt',
    'out8_night.txt'
]

for out_file in output_files:
    out_path = os.path.join(output_txt_dir, out_file)
    with open(out_path, 'w') as f:
        # Write header and sample data that read_helper can parse
        f.write('Precision: 0.85 Recall: 0.90 F-measure: 0.875\n')

# Create a mock detect directory
detect_dir = os.path.join(output_path, 'exp_name')
os.makedirs(detect_dir, exist_ok=True)

ARGS = {
    'data_dir': data_dir,
    'exp_name': 'exp_name',
    'output_path': output_path,
    'category': 'test_all'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
call_culane_eval_custom_sampling Ran
ran on a synthesized input
dongkwonjin/Eigenlanes/Modeling/culane/code/evaluation/eval_culane_official.py
code served (permissive licence) · get_code("1a5509297a567f4c")
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 dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os
import tempfile

# Create temporary directories for the function to work with
temp_dir = tempfile.mkdtemp()
results_dir = os.path.join(temp_dir, 'results')
list_dir = os.path.join(temp_dir, 'list')
os.makedirs(results_dir, exist_ok=True)
os.makedirs(list_dir, exist_ok=True)

# Create a mock datalist.txt file
datalist_path = os.path.join(list_dir, 'datalist.txt')
with open(datalist_path, 'w') as f:
    f.write('mock datalist content\n')

# Create mock data directory
data_dir = os.path.join(temp_dir, 'data')
os.makedirs(data_dir, exist_ok=True)

# Create a mock output directory with exp_name subdirectory
exp_name = 'test_exp'
detect_dir = os.path.join(results_dir, exp_name)
os.makedirs(detect_dir, exist_ok=True)

# Create a mock output file that read_helper will parse
txt_dir = os.path.join(results_dir, 'txt')
os.makedirs(txt_dir, exist_ok=True)
out_file = os.path.join(txt_dir, 'out.txt')
with open(out_file, 'w') as f:
    f.write('header\n')
    f.write('precision: 0.95 recall: 0.87 f1: 0.91\n')

ARGS = {
    'data_dir': data_dir,
    'exp_name': exp_name,
    'output_path': results_dir,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
discrete_cross_iou Ran
ran on a synthesized input
dongkwonjin/Eigenlanes/Modeling/culane/code/evaluation/eval_culane_laneatt.py
code served (permissive licence) · get_code("2c8bbea9efb89e40")
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
import cv2

# Create sample lane data - each lane is a sequence of (x, y) points
# We need at least 2 points per lane for the zip(lane[:-1], lane[1:]) to work

# Sample lane 1: roughly horizontal lane
lane1 = np.array([
    [100, 200],
    [200, 205],
    [300, 210],
    [400, 215]
], dtype=np.float32)

# Sample lane 2: another lane
lane2 = np.array([
    [150, 250],
    [250, 255],
    [350, 260],
    [450, 265]
], dtype=np.float32)

# Sample lane 3: overlapping with lane 1
lane3 = np.array([
    [120, 210],
    [220, 215],
    [320, 220],
    [420, 225]
], dtype=np.float32)

# xs: list of predicted lanes
xs = [lane1, lane2]

# ys: list of ground truth lanes
ys = [lane1, lane3]

ARGS = {
    "xs": xs,
    "ys": ys,
    "width": 30,
    "img_shape": (590, 1640, 3)
}
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 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
draw_lane Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
dongkwonjin/Eigenlanes/Modeling/culane/code/evaluation/eval_culane_laneatt.py
code served (permissive licence) · get_code("b274c90d2c686b65")
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 (100, 100, 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 small lane array with coordinate pairs (x, y)
# Shape: (5, 2) - 5 points, each with x and y coordinate
lane = np.array([
    [10, 20],
    [15, 30],
    [20, 40],
    [25, 50],
    [30, 60]
], dtype=np.float32)

# Create an image with specific shape (100 height, 100 width, 3 channels for BGR)
img_shape = (100, 100, 3)
img = np.zeros(img_shape, dtype=np.uint8)

ARGS = {
    "lane": lane,
    "img": img,
    "img_shape": img_shape,
    "width": 30
}
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 (100, 100, 3) — shape (100, 100, 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
l2_normalization Ran
ran on a synthesized input
dongkwonjin/Eigenlanes/Modeling/culane/code/networks/model.py
code served (permissive licence) · get_code("0dd80b3d6cfa089b")
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, 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 torch

torch.manual_seed(0)

# The function expects a tensor x with at least 2 dimensions
# It computes L2 normalization along dimension 1
# We need a batch of vectors to normalize

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 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
read_helper Ran
ran; our contract draft was wrong, not the code
dongkwonjin/Eigenlanes/Modeling/culane/code/evaluation/eval_culane_official.py
code served (permissive licence) · get_code("a82bfd9d8b8b5cee")
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 dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import os

# Create a temporary file with test data
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_path = temp_file.name

# Write test data in the format expected by read_helper
# The function expects: key1: value1 key2: value2 ...
# It skips the first line, then splits on spaces
# It assumes odd indices are values (1, 3, 5...) and even indices are keys (0, 2, 4...)
# Keys end with ':' which gets stripped

test_data = """header_line_to_skip
name: Alice age: 30 city: NYC score: 95.5
"""

temp_file.write(test_data)
temp_file.close()

ARGS = {
    'path': temp_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
to_np Ran
ran on a synthesized input
dongkwonjin/Eigenlanes/Modeling/culane/code/libs/utils.py
code served (permissive licence) · get_code("90d5599d1ec3e4be")
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 torch

torch.manual_seed(0)

# The function to_np takes a tensor with a .cpu() method and converts it to numpy
# Create a small tensor on CPU
data = torch.randn(2, 4)

ARGS = {
    'data': data
}
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 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
to_np2 Ran
ran on a synthesized input
dongkwonjin/Eigenlanes/Modeling/culane/code/libs/utils.py
code served (permissive licence) · get_code("595a24f015a16800")
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 torch
import numpy as np

torch.manual_seed(0)

# Create a small tensor on CPU
tensor_data = torch.randn(2, 4)

ARGS = {
    "data": tensor_data
}
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, 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
to_tensor Ran
ran on a synthesized input
dongkwonjin/Eigenlanes/Modeling/culane/code/libs/utils.py
code served (permissive licence) · get_code("60217905378521fd")
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, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# The function expects 'data' parameter that is a numpy array
# It will call torch.from_numpy(data) and then .cuda()
# We need to provide a numpy array (CPU only - don't call .cuda() ourselves)

data = np.random.randn(2, 4).astype(np.float32)

ARGS = {
    'data': data
}
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, 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
parse_args Not yet run
unverified (harvested, no recorded run)
dongkwonjin/Eigenlanes/Modeling/culane/code/options/args.py
code served (permissive licence) · get_code("739b1ab73531b9be")
How it ran

no invocation recorded.

prepare_model Not yet run
unverified (harvested, no recorded run)
dongkwonjin/Eigenlanes/Modeling/culane/code/libs/prepare.py
code served (permissive licence) · get_code("84d45bc45745d667")
How it ran

no invocation recorded.

save_model_max Not yet run
unverified (harvested, no recorded run)
dongkwonjin/Eigenlanes/Modeling/culane/code/libs/save_model.py
code served (permissive licence) · get_code("716bf70ef00f9d82")
How it ran

no invocation recorded.

save_model_max_upper Not yet run
unverified (harvested, no recorded run)
dongkwonjin/Eigenlanes/Modeling/culane/code/libs/save_model.py
code served (permissive licence) · get_code("e26fcba793c2928d")
How it ran

no invocation recorded.

update_test_dataloader Not yet run
unverified (harvested, no recorded run)
dongkwonjin/Eigenlanes/Modeling/culane/code/libs/prepare.py
code served (permissive licence) · get_code("1926fe1dc21a97b1")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 6 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 9 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
call_culane_eval_custom 1 other paper
1 later
2408.07486 (2024-08)
OMR: Occlusion-Aware Memory-Based Renement for Video Lane Detection
draw_lane 1 other paper
1 later
2408.07486 (2024-08)
OMR: Occlusion-Aware Memory-Based Renement for Video Lane Detection
read_helper 1 other paper
1 later
2408.07486 (2024-08)
OMR: Occlusion-Aware Memory-Based Renement for Video Lane Detection
to_np 1 other paper
1 dated earlier
2007.08139 (2020-07)
Interactive Video Object Segmentation Using Global and Local Transfer Modules
to_np2 1 other paper
1 dated earlier
2007.08139 (2020-07)
Interactive Video Object Segmentation Using Global and Local Transfer Modules
to_tensor 1 other paper
1 dated earlier
2007.08139 (2020-07)
Interactive Video Object Segmentation Using Global and Local Transfer Modules

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

A novel algorithm to detect road lanes in the eigenlane space is proposed in this paper. First, we introduce the notion of eigenlanes, which are data-driven descriptors for structurally diverse lanes, including curved, as well as straight, lanes. To obtain eigenlanes, we perform the best rank-M approximation of a lane matrix containing all lanes in a training set. Second, we generate a set of lane candidates by clustering the training lanes in the eigenlane space. Third, using the lane candidates, we determine an optimal set of lanes by developing an anchor-based detection network, called SIIC-Net. Experimental results demonstrate that the proposed algorithm provides excellent detection performance for structurally diverse lanes. Our codes are available at https://github.com/dongkwonjin/Eigenlanes.

For agents

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

get_harvested_code_for_paper("2203.15302")
get_code_for_paper("2203.15302")
have("2203.15302")

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

curl https://syntology.ai/api/ran/2203.15302.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.15302.svg)](https://syntology.ai/paper/2203.15302)

Connect an agent — have() is free.