SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.07431 · 2020

A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detection

arXiv · PDF · Open in the Atlas

Code that ran

5 of 7 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 5 have no contract verdict; 0 failures of our instrument; 2 no recorded run), measured 2026-11-21; 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/2005.07431.json · badge: /api/ran/2005.07431.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
TUMFTM/CameraRadarFusionNet canonical (classifier label)
classifier basis: census
5 ran · 2 no recorded run
FunctionStatusWhere it lives
bbox_transform Ran
ran on a synthesized input
TUMFTM/CameraRadarFusionNet/crfnet/utils/anchor_calc.py
code served (permissive licence) · get_code("e43df466ae51b53d")
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 small anchor boxes (batch of 2 anchors)
# Format: [x1, y1, x2, y2]
anchors = np.array([
    [10.0, 10.0, 50.0, 50.0],
    [20.0, 20.0, 60.0, 60.0]
], dtype=np.float32)

# Create ground truth boxes (batch of 2 boxes)
# Format: [x1, y1, x2, y2]
gt_boxes = np.array([
    [12.0, 12.0, 48.0, 48.0],
    [22.0, 22.0, 58.0, 58.0]
], dtype=np.float32)

# Create mean and std arrays
mean = np.array([0.0, 0.0, 0.0, 0.0], dtype=np.float32)
std = np.array([0.2, 0.2, 0.2, 0.2], dtype=np.float32)

ARGS = {
    'anchors': anchors,
    'gt_boxes': gt_boxes,
    'mean': mean,
    'std': std
}
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
binary_focal_loss Ran
ran on a synthesized input
TUMFTM/CameraRadarFusionNet/crfnet/model/losses_neural_filter.py
code served (permissive licence) · get_code("3aed4867ebd731ad")
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 tensorflow as tf

# Create a simple loss function that the binary_focal_loss will wrap
def base_loss_fn(y_true, y_pred):
    """Simple binary crossentropy loss function"""
    return tf.keras.losses.binary_crossentropy(y_true, y_pred)

# Create sample tensors for testing
batch_size = 2
y_true = tf.constant([[0.1], [0.9]], dtype=tf.float32)
y_pred = tf.constant([[0.2], [0.8]], dtype=tf.float32)

ARGS = {
    'loss_fn': base_loss_fn,
    'threshold': 0.5,
    'alpha': 0.2,
    'gamma': 2.0
}
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 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
guess_shapes Ran
ran on a synthesized input
TUMFTM/CameraRadarFusionNet/crfnet/utils/anchor.py
code served (permissive licence) · get_code("a55c4938e127f333")
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 2, dtype family int; 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

# Define arguments for guess_shapes function
image_shape = (480, 640)  # Standard image height and width
pyramid_levels = [0, 1, 2, 3]  # Pyramid levels to use

ARGS = {
    "image_shape": image_shape,
    "pyramid_levels": pyramid_levels,
}
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 list, ndim 2, dtype family int — 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
label_color Ran
ran on a synthesized input
TUMFTM/CameraRadarFusionNet/crfnet/utils/colors.py
code served (permissive licence) · get_code("3b7ba9fb145959ea")
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 int; 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 warnings

colors = [[31, 0, 255], [0, 159, 255], [255, 95, 0], [255, 19, 0], [255, 0, 0], [255, 38, 0], [0, 255, 25], [255, 0, 133], [255, 172, 0], [108, 0, 255], [0, 82, 255], [0, 255, 6], [255, 0, 152], [223, 0, 255], [12, 0, 255], [0, 255, 178], [108, 255, 0], [184, 0, 255], [255, 0, 76], [146, 255, 0], [51, 0, 255], [0, 197, 255], [255, 248, 0], [255, 0, 19], [255, 0, 38], [89, 255, 0], [127, 255, 0], [255, 153, 0], [0, 255, 255], [0, 255, 216], [0, 255, 121], [255, 0, 248], [70, 0, 255], [0, 255, 159], [0, 216, 255], [0, 6, 255], [0, 63, 255], [31, 255, 0], [255, 57, 0], [255, 0, 210], [0, 255, 102], [242, 255, 0], [255, 191, 0], [0, 255, 63], [255, 0, 95], [146, 0, 255], [184, 255, 0], [255, 114, 0], [0, 255, 235], [255, 229, 0], [0, 178, 255], [255, 0, 114], [255, 0, 57], [0, 140, 255], [0, 121, 255], [12, 255, 0], [255, 210, 0], [0, 255, 44], [165, 255, 0], [0, 25, 255], [0, 255, 140], [0, 101, 255], [0, 255, 82], [223, 255, 0], [242, 0, 255], [89, 0, 255], [165, 0, 255], [70, 255, 0], [255, 0, 172], [255, 76, 0], [203, 255, 0], [204, 0, 255], [255, 0, 229], [255, 133, 0], [127, 0, 255], [0, 235, 255], [0, 255, 197], [255, 0, 191], [0, 44, 255], [50, 255, 0]]

def label_color(label):
    """ Return a color from a set of predefined colors. Contains 80 colors in total.

    Args
        label: The label to get the color for.

    Returns
        A list of three values representing a RGB color.

        If no color is defined for a certain label, the color green is returned and a warning is printed.
    """
    if label < len(colors):
        return colors[label]
    else:
        warnings.warn('Label {} has no color, returning default.'.format(label))
        return (0, 255, 0)

ARGS = {
    'label': 5
}
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 int — 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
roc_auc_score Ran
ran on a synthesized input
TUMFTM/CameraRadarFusionNet/crfnet/model/losses_neural_filter.py
code served (permissive licence) · get_code("aa5c45139a89f1db")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Create small TensorFlow tensors for testing
# y_true: binary labels (0 or 1)
y_true = tf.constant([1.0, 0.0, 1.0, 0.0], dtype=tf.float32)

# y_pred: predicted probabilities/scores
y_pred = tf.constant([0.9, 0.2, 0.8, 0.3], dtype=tf.float32)

ARGS = {
    'y_true': y_true,
    'y_pred': y_pred,
}
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 EagerTensor, 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
anchor_targets_bbox Not yet run
unverified (harvested, no recorded run)
TUMFTM/CameraRadarFusionNet/crfnet/utils/anchor_calc.py
code served (permissive licence) · get_code("ceabdb9b27d96155")
How it ran

no invocation recorded.

compute_gt_annotations Not yet run
unverified (harvested, no recorded run)
TUMFTM/CameraRadarFusionNet/crfnet/utils/anchor_calc.py
code served (permissive licence) · get_code("a6fe23a09655be60")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Object detection in camera images, using deep learning has been proven successfully in recent years. Rising detection rates and computationally efficient network structures are pushing this technique towards application in production vehicles. Nevertheless, the sensor quality of the camera is limited in severe weather conditions and through increased sensor noise in sparsely lit areas and at night. Our approach enhances current 2D object detection networks by fusing camera data and projected sparse radar data in the network layers. The proposed CameraRadarFusionNet (CRF-Net) automatically learns at which level the fusion of the sensor data is most beneficial for the detection result. Additionally, we introduce BlackIn, a training strategy inspired by Dropout, which focuses the learning on a specific sensor type. We show that the fusion network is able to outperform a state-of-the-art image-only network for two different datasets. The code for this research will be made available to the public at: https://github.com/TUMFTM/CameraRadarFusionNet.

For agents

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

get_harvested_code_for_paper("2005.07431")
get_code_for_paper("2005.07431")
have("2005.07431")

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

curl https://syntology.ai/api/ran/2005.07431.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.07431.svg)](https://syntology.ai/paper/2005.07431)

Connect an agent — have() is free.