SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.04078 · 2020

A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird's Eye View

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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 6 have no contract verdict; 0 failures of our instrument; 0 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/2005.04078.json · badge: /api/ran/2005.04078.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
ika-rwth-aachen/Cam2BEV canonical (classifier label)
classifier basis: census
5 ran · 0 no recorded run
ika-rwth-aachen/etsi_its_messages community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
abspath Ran
ran on a synthesized input
ika-rwth-aachen/Cam2BEV/model/utils.py
code served (permissive licence) · get_code("2395b4c02267027a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import os

# The function abspath takes a single parameter 'path' which is a string
# It uses os.path.expanduser() and os.path.abspath() on it
# Both of these functions expect a string-like path argument

ARGS = {
    "path": "~/test_directory/file.txt"
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
decoder Ran
ran on a synthesized input
ika-rwth-aachen/Cam2BEV/model/architecture/uNetXST.py
code served (permissive licence) · get_code("ddfa1f70e251fee1")
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 KerasTensor. 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
from tensorflow.keras.layers import Dense, Conv2D, Conv2DTranspose, MaxPooling2D
from tensorflow.keras.layers import BatchNormalization, Dropout
from tensorflow.keras.layers import Concatenate
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input

# Create a minimal set of encoder layers to pass to the decoder
# We need a list of tensors/layer outputs with sufficient depth

# Create input tensor
input_tensor = Input(shape=(32, 32, 3))

# Build encoder_layers list with 3 layers (for udepth=3)
# Each layer should have progressively smaller spatial dimensions
# Layer 0: 32x32x8
layer0 = Conv2D(filters=8, kernel_size=(3, 3), padding='same', activation=tf.nn.relu)(input_tensor)
layer0 = MaxPooling2D(pool_size=(2, 2))(layer0)

# Layer 1: 16x16x16
layer1 = Conv2D(filters=16, kernel_size=(3, 3), padding='same', activation=tf.nn.relu)(layer0)
layer1 = MaxPooling2D(pool_size=(2, 2))(layer1)

# Layer 2: 8x8x32 (deepest encoder layer, starting point for decoder)
layer2 = Conv2D(filters=32, kernel_size=(3, 3), padding='same', activation=tf.nn.relu)(layer1)
layer2 = MaxPooling2D(pool_size=(2, 2))(layer2)

encoder_layers = [layer0, layer1, layer2]

ARGS = {
    'encoder_layers': encoder_layers,
    'udepth': 3,
    'filters1': 8,
    'kernel_size': (3, 3),
    'activation': tf.nn.relu,
    'batch_norm': True,
    'dropout': 0.1
}
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 KerasTensor — a KerasTensor 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
encoder Ran
ran on a synthesized input
ika-rwth-aachen/Cam2BEV/model/architecture/uNetXST.py
code served (permissive licence) · get_code("c0039d5cb7a69174")
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 list. 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
from tensorflow.keras.layers import Input

# Create a small input tensor for the encoder
# The encoder expects a 4D tensor: (batch_size, height, width, channels)
batch_size = 2
height = 4
width = 3
input_channels = 1

# Create an Input layer as the function expects
input_tensor = Input(shape=(height, width, input_channels))

ARGS = {
    'input': input_tensor,
    'udepth': 3,
    'filters1': 8,
    'kernel_size': (3, 3),
    'activation': tf.nn.relu,
    'batch_norm': True,
    'dropout': 0.1,
}
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 list — a list 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
get_files_in_folder Ran
ran on a synthesized input
ika-rwth-aachen/Cam2BEV/model/utils.py
code served (permissive licence) · get_code("32c0a561973913e5")
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 list, 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 os
import tempfile
import shutil

# Create a temporary directory with some test files
temp_dir = tempfile.mkdtemp()
test_files = ['file1.txt', 'file2.txt', 'file3.txt']
for filename in test_files:
    filepath = os.path.join(temp_dir, filename)
    with open(filepath, 'w') as f:
        f.write('test content')

ARGS = {
    'folder': temp_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 list, ndim 1, 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
get_t_its Ran
ran on a synthesized input
ika-rwth-aachen/etsi_its_messages/etsi_its_msgs_utils/samples/utils.py
code served (permissive licence) · get_code("0a11a74a64c6dd13")
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 int, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# The function get_t_its takes a single parameter: unix_nanoseconds
# It performs arithmetic operations on it:
# - multiplies by 1e-06
# - adds and subtracts constants
# - converts to int
# So we need to pass an integer or numeric value representing nanoseconds

# A reasonable unix timestamp in nanoseconds (e.g., Jan 1, 2004 + some offset)
unix_nanoseconds = int(1072915200 * 1e9 + 1e9)  # 1 second after 2004-01-01

ARGS = {
    "unix_nanoseconds": unix_nanoseconds
}
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 int, ndim 0, dtype family int, 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
load_module Ran
ran on a synthesized input
ika-rwth-aachen/Cam2BEV/model/utils.py
code served (permissive licence) · get_code("6965945ec615f691")
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 module. 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 sys
import tempfile
import importlib.util

# Create a temporary Python module file to load
temp_dir = tempfile.mkdtemp()
module_file = os.path.join(temp_dir, "test_module.py")

# Write a simple valid Python module to the temp file
with open(module_file, "w") as f:
    f.write("""
def hello():
    return "Hello from test module"

class TestClass:
    def __init__(self):
        self.value = 42
""")

ARGS = {
    "module_file": module_file
}
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 module — a module output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a module 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

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 6 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.

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

Accurate environment perception is essential for automated driving. When using monocular cameras, the distance estimation of elements in the environment poses a major challenge. Distances can be more easily estimated when the camera perspective is transformed to a bird's eye view (BEV). For flat surfaces, Inverse Perspective Mapping (IPM) can accurately transform images to a BEV. Three-dimensional objects such as vehicles and vulnerable road users are distorted by this transformation making it difficult to estimate their position relative to the sensor. This paper describes a methodology to obtain a corrected 360° BEV image given images from multiple vehicle-mounted cameras. The corrected BEV image is segmented into semantic classes and includes a prediction of occluded areas. The neural network approach does not rely on manually labeled data, but is trained on a synthetic dataset in such a way that it generalizes well to real-world data. By using semantically segmented images as input, we reduce the reality gap between simulated and real-world data and are able to show that our method can be successfully applied in the real world. Extensive experiments conducted on the synthetic data demonstrate the superiority of our approach compared to IPM. Source code and datasets are available at https://github.com/ika-rwth-aachen/Cam2BEV

For agents

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

get_harvested_code_for_paper("2005.04078")
get_code_for_paper("2005.04078")
have("2005.04078")

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

curl https://syntology.ai/api/ran/2005.04078.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.04078.svg)](https://syntology.ai/paper/2005.04078)

Connect an agent — have() is free.