SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.06992 · 2018

Infrared and Visible Image Fusion using a Deep Learning Framework

arXiv · PDF · Open in the Atlas

Code that ran

9 of 16 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; 2 failures of our instrument; 7 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/1804.06992.json · badge: /api/ran/1804.06992.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
JorgeFCS/Deep-Learning-fire-segmentation community (classifier label)
classifier basis not recorded on the link
9 ran · 7 no recorded run
FunctionStatusWhere it lives
a_central_crop Ran
ran on a synthesized input
JorgeFCS/Deep-Learning-fire-segmentation/Functions/data_augmentation.py
code served (permissive licence) · get_code("dcd39d13741d9215")
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 3, 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 tensorflow as tf
import numpy as np

# Create a small image tensor for the function
# The function expects an image, likely in format (height, width, channels)
# We'll create a batch of 2 images with height=256, width=256, and 3 channels (RGB)
image_data = np.random.rand(256, 256, 3).astype(np.float32)
image_tensor = tf.constant(image_data)

ARGS = {
    "image": image_tensor
}
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 3, dtype family float — no output shape is stated: observe_signature.py recorded SymbolicTensor ndim 3, which disagrees with the fixture run
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
a_mirror_image Ran
ran on a synthesized input
JorgeFCS/Deep-Learning-fire-segmentation/Functions/data_augmentation.py
code served (permissive licence) · get_code("e80b7eab36222fa2")
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 3, dtype family float, shape (384, 512, 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 tensorflow as tf
import numpy as np

# Create a small test image tensor
# a_mirror_image expects an image tensor that can be processed by TensorFlow
# The function flips it horizontally and resizes to [384, 512]
# We'll create a small image with shape [height, width, channels]
image_np = np.random.randint(0, 256, size=(64, 80, 3), dtype=np.uint8)
image_tensor = tf.constant(image_np)

ARGS = {
    "image": image_tensor
}
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 3, dtype family float, shape (384, 512, 3) — shape (384, 512, 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
a_rotate_180 Ran
ran on a synthesized input
JorgeFCS/Deep-Learning-fire-segmentation/Functions/data_augmentation.py
code served (permissive licence) · get_code("022f89502db14646")
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 3, dtype family float, shape (384, 512, 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 tensorflow as tf
import numpy as np

# Create a small test image tensor
# TensorFlow expects images as tensors with shape (height, width, channels)
# Using a small image: 4 height x 3 width x 3 channels (RGB)
image_data = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8)
image_tensor = tf.convert_to_tensor(image_data, dtype=tf.uint8)

ARGS = {
    "image": image_tensor
}
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 3, dtype family float, shape (384, 512, 3) — shape (384, 512, 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
cross_entropy Ran
ran on a synthesized input
JorgeFCS/Deep-Learning-fire-segmentation/Models/loss_functions.py
code served (permissive licence) · get_code("3707bc0d98adcbee")
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 sample tensors for y_true and y_pred
# Using batch size 2 and feature dimension 4
batch_size = 2
feature_dim = 4

# y_true: binary labels, shape (2, 4)
y_true = tf.constant(np.random.randint(0, 2, size=(batch_size, feature_dim)), dtype=tf.float32)

# y_pred: logits (raw model outputs), shape (2, 4)
y_pred = tf.constant(np.random.randn(batch_size, feature_dim).astype(np.float32), 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
dice_loss Ran
ran on a synthesized input
JorgeFCS/Deep-Learning-fire-segmentation/Models/loss_functions.py
code served (permissive licence) · get_code("9cb171702656ea9e")
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 1, dtype family float, shape (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 tensorflow as tf
import numpy as np

# Create small valid tensors for the dice_loss function
# The function expects tensors with shape that has either 4 or 5 dimensions
# (batch_size, spatial_dims..., num_classes)

# For 4D case: (batch, height, width, num_classes)
batch_size = 2
height = 4
width = 3
num_classes = 5

# Create y_true and y_pred as TensorFlow tensors
# y_true should be binary (0 or 1) - ground truth labels
y_true_data = np.random.randint(0, 2, size=(batch_size, height, width, num_classes)).astype(np.float32)
y_true = tf.constant(y_true_data)

# y_pred should be probabilities (0 to 1) - model predictions
y_pred_data = np.random.rand(batch_size, height, width, num_classes).astype(np.float32)
y_pred = tf.constant(y_pred_data)

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 1, dtype family float, shape (2,) — shape (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
downsample Ran
ran; our contract draft was wrong, not the code
JorgeFCS/Deep-Learning-fire-segmentation/Models/fire_gan.py
code served (permissive licence) · get_code("68922abe9828bbd9")
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 Sequential. 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

ARGS = {
    'filters': 64,
    'size': 4,
    'apply_batchnorm': True,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential 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
tversky_loss Ran
ran on a synthesized input
JorgeFCS/Deep-Learning-fire-segmentation/Models/loss_functions.py
code served (permissive licence) · get_code("80752ad8dcc7619b")
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 1, dtype family float, shape (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 tensorflow as tf
from tensorflow.keras import backend as K
import numpy as np

# Create small test tensors for the tversky_loss function
# The function expects tensors with shape that is either 4D or 5D
# (batch_size, spatial_dim1, spatial_dim2, channels) for 4D
# (batch_size, spatial_dim1, spatial_dim2, spatial_dim3, channels) for 5D

# Create 4D tensors (batch_size=2, height=3, width=4, channels=5)
batch_size = 2
height = 3
width = 4
num_channels = 5

# y_true: binary ground truth labels
y_true = tf.constant(
    np.random.randint(0, 2, size=(batch_size, height, width, num_channels)),
    dtype=tf.float32
)

# y_pred: predicted probabilities (should be between 0 and 1)
y_pred = tf.constant(
    np.random.rand(batch_size, height, width, num_channels).astype(np.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 1, dtype family float, shape (2,) — shape (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
upsample Ran
ran; our contract draft was wrong, not the code
JorgeFCS/Deep-Learning-fire-segmentation/Models/fire_gan.py
code served (permissive licence) · get_code("326ce7182e5c2db8")
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 Sequential. 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

ARGS = {
    "filters": 64,
    "size": 4,
    "apply_dropout": True,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential 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
yellow_block Ran
ran on a synthesized input
JorgeFCS/Deep-Learning-fire-segmentation/Models/choi.py
code served (permissive licence) · get_code("7af2abc1c0b98fc1")
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 4, dtype family float, shape (2, 4, 3, 8) 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

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

# Create a small input tensor with shape (batch_size, height, width, channels)
# batch=2, height=4, width=3, channels=5
x = tf.random.normal((2, 4, 3, 5), dtype=tf.float32)

# Number of filters for the convolutional layers
num_filters = 8

ARGS = {
    'x': x,
    'num_filters': num_filters
}
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 4, dtype family float, shape (2, 4, 3, 8) — shape (2, 4, 3, 8) 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
create_g2_firegan Not yet run
unverified (harvested, no recorded run)
JorgeFCS/Deep-Learning-fire-segmentation/Models/fire_gan.py
code served (permissive licence) · get_code("7c3bff665310a4cf")
How it ran

no invocation recorded.

decode_img Not yet run
unverified (harvested, no recorded run)
JorgeFCS/Deep-Learning-fire-segmentation/Functions/image_processing.py
code served (permissive licence) · get_code("c01f8ee6857e6969")
How it ran

no invocation recorded.

decode_mask Not yet run
unverified (harvested, no recorded run)
JorgeFCS/Deep-Learning-fire-segmentation/Functions/image_processing.py
code served (permissive licence) · get_code("604effdb50d7847e")
How it ran

no invocation recorded.

expend_as Not yet run
unverified (harvested, no recorded run)
JorgeFCS/Deep-Learning-fire-segmentation/Models/attention_modules.py
code served (permissive licence) · get_code("5a19ddee988093ce")
How it ran

no invocation recorded.

meca_block Not yet run
unverified (harvested, no recorded run)
JorgeFCS/Deep-Learning-fire-segmentation/Models/attention_modules.py
code served (permissive licence) · get_code("0ad1449cd4e8d3d7")
How it ran

no invocation recorded.

process_path_img Not yet run
unverified (harvested, no recorded run)
JorgeFCS/Deep-Learning-fire-segmentation/Functions/image_processing.py
code served (permissive licence) · get_code("750dceaac9af934a")
How it ran

no invocation recorded.

purple_block Not yet run
unverified (harvested, no recorded run)
JorgeFCS/Deep-Learning-fire-segmentation/Models/choi.py
code served (permissive licence) · get_code("4649d243f332314e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 14 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
downsample 1 other paper
1 dated earlier
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
upsample 1 other paper
1 dated earlier
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks

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 recent years, deep learning has become a very active research tool which is used in many image processing fields. In this paper, we propose an effective image fusion method using a deep learning framework to generate a single image which contains all the features from infrared and visible images. First, the source images are decomposed into base parts and detail content. Then the base parts are fused by weighted-averaging. For the detail content, we use a deep learning network to extract multi-layer features. Using these features, we use l_1-norm and weighted-average strategy to generate several candidates of the fused detail content. Once we get these candidates, the max selection strategy is used to get final fused detail content. Finally, the fused image will be reconstructed by combining the fused base part and detail content. The experimental results demonstrate that our proposed method achieves state-of-the-art performance in both objective assessment and visual quality. The Code of our fusion method is available at https://github.com/hli1221/imagefusion_deeplearning

For agents

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

get_harvested_code_for_paper("1804.06992")
get_code_for_paper("1804.06992")
have("1804.06992")

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

curl https://syntology.ai/api/ran/1804.06992.json

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

[![Syntology run record](https://syntology.ai/api/ran/1804.06992.svg)](https://syntology.ai/paper/1804.06992)

Connect an agent — have() is free.