SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1703.07511 · 2017

Deep Photo Style Transfer

arXiv · PDF · Open in the Atlas

Code that ran

17 of 24 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 15 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/1703.07511.json · badge: /api/ran/1703.07511.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
7-B/yoco community (classifier label)
classifier basis not recorded on the link
7 ran · 1 no recorded run
ritesh2212/DeepPhotoStyle_pytorch-master reimplementation (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
dedekinds/The-Color-Transfer-of-Animes-Characters-Images community (classifier label)
classifier basis not recorded on the link
2 ran · 3 no recorded run
IdanAzuri/pytorch_fewshot_with_deep_photo reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
clovaai/WCT2 reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
KangDo96/Github-Ranking community (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
xuberance137/styleflow reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
bgr2rgb Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
dedekinds/The-Color-Transfer-of-Animes-Characters-Images/photo_style.py
code served (permissive licence) · get_code("25645bb38ddc950c")
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 float, shape (4, 3, 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 numpy as np
import torch

torch.manual_seed(0)

# The function expects a numpy array (since it uses slicing [:, :, ::-1])
# with shape (height, width, channels) where channels=3 for BGR
bgr_array = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8).astype(np.float32)

ARGS = {
    "bgr": bgr_array,
    "vgg_mean": False
}
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 3, dtype family float, shape (4, 3, 3) — shape (4, 3, 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
get_input_optimizer Ran
ran; our contract draft was wrong, not the code
ritesh2212/DeepPhotoStyle_pytorch-master/neural_style.py
pointer only (licence: NONE) · get_code("8f043783be05520d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ritesh2212/DeepPhotoStyle_pytorch-master 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_input_optimizer Ran
ran; our contract draft was wrong, not the code
IdanAzuri/pytorch_fewshot_with_deep_photo/neural_style.py
pointer only (licence: NONE) · get_code("9269e2b72f0e2876")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, IdanAzuri/pytorch_fewshot_with_deep_photo 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_palette Ran
ran, honoured the contract we drafted
7-B/yoco/segmentation/evaluate.py
code served (permissive licence) · get_code("26664d79586aad5a")
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 torch
import numpy as np

def get_palette(num_cls):
    """ Returns the color map for visualizing the segmentation mask.
    Args:
        num_cls: Number of classes
    Returns:
        The color map
    """
    n = num_cls
    palette = [0] * (n * 3)
    for j in range(0, n):
        lab = j
        palette[j * 3 + 0] = 0
        palette[j * 3 + 1] = 0
        palette[j * 3 + 2] = 0
        i = 0
        while lab:
            palette[j * 3 + 0] |= (lab >> 0 & 1) << 7 - i
            palette[j * 3 + 1] |= (lab >> 1 & 1) << 7 - i
            palette[j * 3 + 2] |= (lab >> 2 & 1) << 7 - i
            i += 1
            lab >>= 3
    return palette

ARGS = {
    "num_cls": 5
}
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 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
get_style_model_and_losses Ran
ran; our contract draft was wrong, not the code
ritesh2212/DeepPhotoStyle_pytorch-master/neural_style.py
pointer only (licence: NONE) · get_code("81173dfd88ec4a96")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ritesh2212/DeepPhotoStyle_pytorch-master 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_style_model_and_losses Ran
ran; our contract draft was wrong, not the code
IdanAzuri/pytorch_fewshot_with_deep_photo/neural_style.py
pointer only (licence: NONE) · get_code("067c53092682afb5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, IdanAzuri/pytorch_fewshot_with_deep_photo 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_style_model_and_losses Ran
ran; our contract draft was wrong, not the code
7-B/yoco/segmentation/torch_neural_style_transfer.py
code served (permissive licence) · get_code("a675446ddbbfbcc1")
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. 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 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
import copy

torch.manual_seed(0)

# Create a minimal CNN with Conv2d, ReLU, MaxPool2d, BatchNorm2d layers
# The function iterates through children and looks for these specific layer types
cnn = nn.Sequential(
    nn.Conv2d(3, 8, kernel_size=3, padding=1),
    nn.ReLU(inplace=True),
    nn.Conv2d(8, 16, kernel_size=3, padding=1),
    nn.ReLU(inplace=True),
    nn.MaxPool2d(kernel_size=2, stride=2),
    nn.Conv2d(16, 32, kernel_size=3, padding=1),
    nn.ReLU(inplace=True),
    nn.Conv2d(32, 64, kernel_size=3, padding=1),
    nn.ReLU(inplace=True),
    nn.MaxPool2d(kernel_size=2, stride=2),
    nn.Conv2d(64, 128, kernel_size=3, padding=1),
    nn.ReLU(inplace=True),
)

# Create small style and content images (batch=2, channels=3, height=4, width=4)
style_img = torch.randn(2, 3, 4, 4)
content_img = torch.randn(2, 3, 4, 4)

# Normalization parameters
normalization_mean = [0.485, 0.456, 0.406]
normalization_std = [0.229, 0.224, 0.225]

# Default layer specifications
content_layers_default = ['conv_4']
style_layers_default = ['conv_1', 'conv_2', 'conv_3', 'conv_4', 'conv_5']

ARGS = {
    'cnn': cnn,
    'normalization_mean': normalization_mean,
    'normalization_std': normalization_std,
    'style_img': style_img,
    'content_img': content_img,
    'content_layers': content_layers_default,
    'style_layers': style_layers_default,
}
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
get_wav Ran
ran; our contract draft was wrong, not the code
clovaai/WCT2/model.py
code served (permissive licence) · get_code("289a3baab5b57fbb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned tuple, 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 torch
import torch.nn as nn
import numpy as np

torch.manual_seed(0)

# The function takes in_channels (int) and pool (bool)
# in_channels: number of input channels for the conv layers
# pool: whether to use Conv2d (True) or ConvTranspose2d (False)

ARGS = {
    'in_channels': 3,
    'pool': True
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple 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
gram_matrix Ran
ran; our contract draft was wrong, not the code
ritesh2212/DeepPhotoStyle_pytorch-master/neural_style.py
pointer only (licence: NONE) · get_code("cda180904c38bf82")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ritesh2212/DeepPhotoStyle_pytorch-master 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.

gram_matrix Ran
ran; our contract draft was wrong, not the code
7-B/yoco/segmentation/torch_neural_style_transfer.py
pointer only (licence: MIT); the stored copy get_code serves, from Oldpan/Deep-Painterly-Harmonization-Pytorch, is pointer only (licence: NONE) · get_code("1090950b58e9358b")
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 Oldpan/Deep-Painterly-Harmonization-Pytorch, 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.

image_resize Ran
ran; our contract draft was wrong, not the code
7-B/yoco/convert.py
code served (permissive licence) · get_code("81841f6d779c16fc")
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 (62, 50, 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 test image
# Using a 100x80 RGB image (height=100, width=80)
image = np.random.randint(0, 256, (100, 80, 3), dtype=np.uint8)

# Define arguments for the function
ARGS = {
    'image': image,
    'width': 50,
    'height': None,
    'inter': cv2.INTER_AREA
}
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 (62, 50, 3) — shape (62, 50, 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
image_resize Ran
ran; our contract draft was wrong, not the code
7-B/yoco/segmentation/merge_image.py
code served (permissive licence) · get_code("146ad565b06fda04")
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 (20, 20, 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 math
import cv2
import numpy as np

# Create a small test image (height=10, width=15, 3 channels for color)
image = np.random.randint(0, 256, (10, 15, 3), dtype=np.uint8)

ARGS = {
    "image": image,
    "width": 20,
    "height": None,
    "inter": cv2.INTER_AREA
}
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 (20, 20, 3) — shape (20, 20, 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
is_image_file Ran
ran, violated the contract we drafted
clovaai/WCT2/transfer.py
code served (permissive licence) · get_code("59848503040bbdac")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned bool, 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.

ARGS = {
    'filename': 'test_image.jpg'
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 bool, 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
repo_to_df Ran
ran; our contract draft was wrong, not the code
KangDo96/Github-Ranking/save_most_stars_forks.py
code served (permissive licence) · get_code("25b81f14a52435da")
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 DataFrame. 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 pandas as pd

# Construct mock repository data structures
repos = [
    {
        'name': 'repo1',
        'stargazers_count': 100,
        'forks_count': 25,
        'language': 'Python',
        'html_url': 'https://github.com/user/repo1',
        'owner': {'login': 'user1'},
        'open_issues_count': 5,
        'pushed_at': '2023-01-15T10:30:00Z',
        'description': 'A sample repository'
    },
    {
        'name': 'repo2',
        'stargazers_count': 250,
        'forks_count': 50,
        'language': 'JavaScript',
        'html_url': 'https://github.com/user/repo2',
        'owner': {'login': 'user2'},
        'open_issues_count': 12,
        'pushed_at': '2023-02-20T14:45:00Z',
        'description': 'Another sample repository'
    }
]

item = 'test_item'

col = ['count', 'item', 'name', 'stargazers_count', 'forks_count', 'language', 'html_url', 'owner', 'open_issues_count', 'pushed_at', 'description']

ARGS = {
    'repos': repos,
    'item': item,
    'col': col
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DataFrame — a DataFrame output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataFrame output the recorded ndim 2 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
rgb2bgr Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
dedekinds/The-Color-Transfer-of-Animes-Characters-Images/photo_style.py
code served (permissive licence) · get_code("887c76559ae8b99a")
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 float, shape (2, 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 numpy as np

torch.manual_seed(0)

# The function rgb2bgr takes:
# - rgb: an array-like object that supports slicing with [:, :, ::-1]
# - vgg_mean: a boolean (default True)

# Create a small RGB image array (height=2, width=4, channels=3)
rgb = np.random.rand(2, 4, 3).astype(np.float32) * 255

ARGS = {
    "rgb": rgb,
    "vgg_mean": True
}
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 3, dtype family float, shape (2, 4, 3) — shape (2, 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
sketch Ran
ran; our contract draft was wrong, not the code
7-B/yoco/convert.py
code served (permissive licence) · get_code("8a715fc3d20336d9")
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 cv2
import os
import numpy as np
import tempfile

# Create a temporary directory for test files
temp_dir = tempfile.mkdtemp()

# Create a small test image file
test_image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
test_image_path = os.path.join(temp_dir, "test_image.jpg")
cv2.imwrite(test_image_path, test_image)

# Define ARGS dictionary with all parameters for the sketch function
ARGS = {
    "path": test_image_path,
    "imgname": "test_image.jpg"
}
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 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
sobel Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
7-B/yoco/convert.py
code served (permissive licence) · get_code("ffb0ca0a0f71ef50")
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 int, shape (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 cv2
import numpy as np

# Create a simple grayscale image for the sobel edge detection
# The function expects an image that cv2.Sobel can process
# cv2.Sobel works with 2D or 3D arrays
img = np.random.randint(0, 256, (4, 3), dtype=np.uint8)

ARGS = {
    "img": img
}
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 int, shape (4, 3) — shape (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
getLaplacian Not yet run
unverified (harvested, no recorded run)
dedekinds/The-Color-Transfer-of-Animes-Characters-Images/closed_form_matting.py
code served (permissive licence) · get_code("db1f82381fe3492d")
How it ran

no invocation recorded.

get_all_repos Not yet run
unverified (harvested, no recorded run)
KangDo96/Github-Ranking/save_most_stars_forks.py
code served (permissive licence) · get_code("2ae68c5edc37dccd")
How it ran

no invocation recorded.

get_api_repos Not yet run
unverified (harvested, no recorded run)
KangDo96/Github-Ranking/save_most_stars_forks.py
code served (permissive licence) · get_code("9ecb8eaa36f40e46")
How it ran

no invocation recorded.

getlaplacian1 Not yet run
unverified (harvested, no recorded run)
dedekinds/The-Color-Transfer-of-Animes-Characters-Images/closed_form_matting.py
code served (permissive licence) · get_code("9ec5126d68c7d179")
How it ran

no invocation recorded.

image_loader Not yet run
unverified (harvested, no recorded run)
7-B/yoco/segmentation/torch_neural_style_transfer.py
code served (permissive licence) · get_code("2d24aafc6d216a66")
How it ran

no invocation recorded.

imread Not yet run
unverified (harvested, no recorded run)
xuberance137/styleflow/neural_style.py
pointer only (licence: NONE) · get_code("e9d9cfa5605ea1a3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, xuberance137/styleflow 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. No invocation recorded.

load_seg Not yet run
unverified (harvested, no recorded run)
dedekinds/The-Color-Transfer-of-Animes-Characters-Images/photo_style.py
code served (permissive licence) · get_code("18c2e14d332c9062")
How it ran

no invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 23 distinct functions with an identity, 7 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 5 later) and 16 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
is_image_file 62 other papers
1 dated earlier, 61 later
1609.04802 (2016-09)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
1710.10916 (2017-10)
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
and 59 more not named here
gram_matrix 12 other papers
1 dated earlier, 11 later
1508.06576 (2015-08)
A Neural Algorithm of Artistic Style
1804.03189 (2018-04)
Deep Painterly Harmonization
1804.07723 (2018-04)
Image Inpainting for Irregular Holes Using Partial Convolutions
and 9 more not named here
get_palette 8 other papers
8 later
1811.11721 (2018-11)
CCNet: Criss-Cross Attention for Semantic Segmentation
1903.04197 (2019-03)
Structured Knowledge Distillation for Dense Prediction
1910.09777 (2019-10)
Self-Correction for Human Parsing
and 5 more not named here
image_loader 3 other papers
3 later
2402.11846 (2024-02)
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
2405.15234 (2024-05)
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
2410.15618 (2024-10)
Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
get_wav 2 other papers
2 later
1802.06474 (2018-02)
A Closed-form Solution to Photorealistic Image Stylization
1903.09760 (2019-03)
Photorealistic Style Transfer via Wavelet Transforms
get_input_optimizer 1 other paper
1 dated earlier
1606.00915 (2016-06)
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
imread 1 other paper
1 dated earlier
1508.06576 (2015-08)
A Neural Algorithm of Artistic Style

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

This paper introduces a deep-learning approach to photographic style transfer that handles a large variety of image content while faithfully transferring the reference style. Our approach builds upon the recent work on painterly transfer that separates style from the content of an image by considering different layers of a neural network. However, as is, this approach is not suitable for photorealistic style transfer. Even when both the input and reference images are photographs, the output still exhibits distortions reminiscent of a painting. Our contribution is to constrain the transformation from the input to the output to be locally affine in colorspace, and to express this constraint as a custom fully differentiable energy term. We show that this approach successfully suppresses distortion and yields satisfying photorealistic style transfers in a broad variety of scenarios, including transfer of the time of day, weather, season, and artistic edits.

For agents

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

get_harvested_code_for_paper("1703.07511")
get_code_for_paper("1703.07511")
have("1703.07511")

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

curl https://syntology.ai/api/ran/1703.07511.json

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

[![Syntology run record](https://syntology.ai/api/ran/1703.07511.svg)](https://syntology.ai/paper/1703.07511)

Connect an agent — have() is free.