SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2009.08679 · 2020

Face Sketch Synthesis with Style Transfer using Pyramid Column Feature

arXiv · PDF · Open in the Atlas

Code that ran

4 of 9 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 4 have no contract verdict; 0 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/2009.08679.json · badge: /api/ran/2009.08679.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
chaofengc/Face-Sketch canonical (classifier label)
classifier basis: census
4 ran · 5 no recorded run
FunctionStatusWhere it lives
cal_DOF Ran
ran on a synthesized input
chaofengc/Face-Sketch/utils/img_process.py
code served (permissive licence) · get_code("64358dec514d42c2")
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 (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 as cv
import numpy as np

torch_manual_seed_called = False
try:
    import torch
    torch.manual_seed(0)
    torch_manual_seed_called = True
except:
    pass

# Create a small test image
# The function expects either a 2D grayscale image or a 3D RGB image
# We'll create a 3D RGB image (height=4, width=3, channels=3) with uint8 values
img = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)

ARGS = {
    "img": img,
    "sigma": 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, 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 (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
deprocess_image Ran
ran on a synthesized input
chaofengc/Face-Sketch/utils/img_process.py
code served (permissive licence) · get_code("584bbcc80a4505a1")
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 (250, 200) 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 as cv

# Create a small numpy array as input
# The function uses .squeeze(), np.clip(), and cv.resize()
# Start with a 3D array that can be squeezed
x = np.random.randint(0, 256, size=(1, 100, 120), dtype=np.uint8)

# Define the arguments dictionary
ARGS = {
    'x': x,
    'size': (200, 250)
}
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 (250, 200) — shape (250, 200) 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
pred_acc Ran
ran on a synthesized input
chaofengc/Face-Sketch/evaluate.py
code served (permissive licence) · get_code("edab3552e66585dc")
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 float64, ndim 0, 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 numpy as np

# Create small PCA-reduced feature matrices
# train_pca: shape (n_train, n_features)
# test_pca: shape (n_test, n_features)
np.random.seed(0)

n_train = 5
n_test = 3
n_features = 4

train_pca = np.random.randn(n_train, n_features).astype(np.float32)
test_pca = np.random.randn(n_test, n_features).astype(np.float32)

# Create labels for training and test sets
# y_train: shape (n_train,) with class indices
# y_test: shape (n_test,) with class indices
y_train = np.array([0, 1, 0, 2, 1], dtype=np.int64)
y_test = np.array([1, 0, 2], dtype=np.int64)

ARGS = {
    'train_pca': train_pca,
    'y_train': y_train,
    'test_pca': test_pca,
    'y_test': y_test,
    'topk': 1
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, 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
preprocess_image Ran
ran on a synthesized input
chaofengc/Face-Sketch/utils/img_process.py
code served (permissive licence) · get_code("aa161d444a9e477f")
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 4, dtype family int, shape (1, 3, 288, 288) 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 as cv
import tempfile
import os

# Create a temporary image file for testing
temp_dir = tempfile.mkdtemp()
image_path = os.path.join(temp_dir, "test_image.png")

# Create a simple test image (BGR format, 3 channels, 100x100)
test_image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
cv.imwrite(image_path, test_image)

ARGS = {
    "image_path": image_path,
    "color": 1,  # cv.IMREAD_COLOR (read as BGR)
    "size": (288, 288)
}
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 4, dtype family int, shape (1, 3, 288, 288) — shape (1, 3, 288, 288) 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
abs_loss Not yet run
unverified (harvested, no recorded run)
chaofengc/Face-Sketch/utils/loss.py
code served (permissive licence) · get_code("6b790ef0426132fa")
How it ran

no invocation recorded.

compare_patch Not yet run
unverified (harvested, no recorded run)
chaofengc/Face-Sketch/utils/compare_patch.py
code served (permissive licence) · get_code("5252377d87336417")
How it ran

no invocation recorded.

gram_matrix Not yet run
unverified (harvested, no recorded run)
chaofengc/Face-Sketch/utils/loss.py
code served (permissive licence) · get_code("b746320437ac4e84")
How it ran

no invocation recorded.

load_dataset Not yet run
unverified (harvested, no recorded run)
chaofengc/Face-Sketch/evaluate.py
code served (permissive licence) · get_code("b462657767571b31")
How it ran

no invocation recorded.

total_variation_loss Not yet run
unverified (harvested, no recorded run)
chaofengc/Face-Sketch/utils/loss.py
code served (permissive licence) · get_code("99b5ef9a37a89e47")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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
gram_matrix 1 other paper
1 dated earlier
1601.04589 (2016-01)
Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis

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 this paper, we propose a novel framework based on deep neural networks for face sketch synthesis from a photo. Imitating the process of how artists draw sketches, our framework synthesizes face sketches in a cascaded manner. A content image is first generated that outlines the shape of the face and the key facial features. Textures and shadings are then added to enrich the details of the sketch. We utilize a fully convolutional neural network (FCNN) to create the content image, and propose a style transfer approach to introduce textures and shadings based on a newly proposed pyramid column feature. We demonstrate that our style transfer approach based on the pyramid column feature can not only preserve more sketch details than the common style transfer method, but also surpasses traditional patch based methods. Quantitative and qualitative evaluations suggest that our framework outperforms other state-of-the-arts methods, and can also generalize well to different test images. Codes are available at https://github.com/chaofengc/Face-Sketch

For agents

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

get_harvested_code_for_paper("2009.08679")
get_code_for_paper("2009.08679")
have("2009.08679")

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

curl https://syntology.ai/api/ran/2009.08679.json

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

[![Syntology run record](https://syntology.ai/api/ran/2009.08679.svg)](https://syntology.ai/paper/2009.08679)

Connect an agent — have() is free.