SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.03059 · 2020

Guided Fine-Tuning for Large-Scale Material Transfer

arXiv · PDF · Open in the Atlas

Code that ran

6 of 13 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, 2 violated it and 3 have no contract verdict; 0 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/2007.03059.json · badge: /api/ran/2007.03059.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
valentin-deschaintre/Guided_fine_tuning_SVBRDF canonical (classifier label)
classifier basis: census
6 ran · 7 no recorded run
FunctionStatusWhere it lives
deprocess Ran
ran, violated the contract we drafted
valentin-deschaintre/Guided_fine_tuning_SVBRDF/helpers.py
code served (permissive licence) · get_code("4288f8e325eb43a4")
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 SymbolicTensor. 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
import numpy as np

# Create a small test image tensor
# The function expects an image and applies (image + 1) / 2
# This is a typical deprocessing operation for images in range [-1, 1]
# Let's create a small image tensor with shape (2, 4, 4, 3) for batch of 2, 4x4 spatial, 3 channels
image_data = np.random.randn(2, 4, 4, 3).astype(np.float32) * 0.5
image = tf.constant(image_data)

ARGS = {
    'image': image
}
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 SymbolicTensor — a SymbolicTensor 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
gaussianWeight Ran
ran on a synthesized input
valentin-deschaintre/Guided_fine_tuning_SVBRDF/testScript_finalTraining.py
code served (permissive licence) · get_code("bbe8d60019ae1d2f")
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 1, dtype family float, shape (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

# The function gaussianWeight takes three scalar or array parameters:
# x: input value(s)
# mu: mean
# sigma: standard deviation (must be positive)

# Create simple scalar values for testing
x_val = np.array([0.0, 1.0, 2.0])
mu_val = 1.0
sigma_val = 0.5

ARGS = {
    "x": x_val,
    "mu": mu_val,
    "sigma": sigma_val
}
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 1, dtype family float, shape (3,) — shape (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
l1 Ran
ran on a synthesized input
valentin-deschaintre/Guided_fine_tuning_SVBRDF/losses.py
code served (permissive licence) · get_code("0a80ad08bd34d0c8")
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 distinct tensors for x and y
# Use different shapes to make dimensions unambiguous
x = tf.constant([[1.0, 2.0, 3.0, 4.0],
                  [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)

y = tf.constant([[1.5, 2.5, 3.5, 4.5],
                  [5.5, 6.5, 7.5, 8.5]], dtype=tf.float32)

ARGS = {
    "x": x,
    "y": y
}
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
lrelu Ran
ran, honoured the contract we drafted
valentin-deschaintre/Guided_fine_tuning_SVBRDF/tfHelpers.py
code served (permissive licence) · get_code("19af0fe9ccd63f6b")
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 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 tensorflow as tf
import numpy as np

# Create a small test tensor
x_value = tf.constant([[1.0, -2.0, 3.0, -4.0],
                       [0.5, -1.5, 2.5, -3.5]], dtype=tf.float32)

# Create a small scalar value for the alpha parameter
a_value = 0.1

ARGS = {
    'x': x_value,
    'a': a_value,
}
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 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
preprocess Ran
ran, violated the contract we drafted
valentin-deschaintre/Guided_fine_tuning_SVBRDF/helpers.py
code served (permissive licence) · get_code("7b296d580bba710b")
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, 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 tensorflow as tf
import numpy as np

# Create a small test image tensor
# The function takes an image and applies: image * 2 - 1
# This is a simple preprocessing operation
image = tf.constant(np.random.rand(2, 4, 4, 3).astype(np.float32))

ARGS = {
    'image': image
}
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, 4, 3) — shape (2, 4, 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
resizeCropAndCreateTestSet Ran
ran on a synthesized input
valentin-deschaintre/Guided_fine_tuning_SVBRDF/testScript_finalTraining.py
code served (permissive licence) · get_code("6f863ea7588c0dcc")
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 numpy as np
import os
import tempfile
import imageio

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

# Create a mock crops image file
# The function expects:
# - crops to be a path to an image file
# - The image height should be divisible by exampleSize (256)
# - The image width should be divisible by 4 (since it splits by 4 on axis=1)
# Create an image with shape (512, 1024, 3) - 2 crops vertically, 4 crops horizontally
crops_image = np.random.randint(0, 255, (512, 1024, 3), dtype=np.uint8)
crops_path = os.path.join(temp_dir, 'test_crops.png')
imageio.imwrite(crops_path, crops_image)

materialName = 'test_material'
output_dir = os.path.join(temp_dir, 'output')

ARGS = {
    'crops': crops_path,
    'materialName': materialName,
    'output_dir': output_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, imageio, numpy — 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
AdaIN Not yet run
unverified (harvested, no recorded run)
valentin-deschaintre/Guided_fine_tuning_SVBRDF/tfHelpers.py
code served (permissive licence) · get_code("83ce7dafef764413")
How it ran

no invocation recorded.

SSIMLoss Not yet run
unverified (harvested, no recorded run)
valentin-deschaintre/Guided_fine_tuning_SVBRDF/losses.py
code served (permissive licence) · get_code("b0198aff441297d9")
How it ran

no invocation recorded.

conv Not yet run
unverified (harvested, no recorded run)
valentin-deschaintre/Guided_fine_tuning_SVBRDF/tfHelpers.py
code served (permissive licence) · get_code("02842c11955ec5af")
How it ran

no invocation recorded.

cropImage Not yet run
unverified (harvested, no recorded run)
valentin-deschaintre/Guided_fine_tuning_SVBRDF/testScript_finalTraining.py
code served (permissive licence) · get_code("ddd86eb2a909cec5")
How it ran

no invocation recorded.

defaultScene Not yet run
unverified (harvested, no recorded run)
valentin-deschaintre/Guided_fine_tuning_SVBRDF/acquisitionScene.py
code served (permissive licence) · get_code("ea769b80518d24b6")
How it ran

no invocation recorded.

defaultSceneSpotLight Not yet run
unverified (harvested, no recorded run)
valentin-deschaintre/Guided_fine_tuning_SVBRDF/acquisitionScene.py
code served (permissive licence) · get_code("9aecc18eca8062e4")
How it ran

no invocation recorded.

logTensor Not yet run
unverified (harvested, no recorded run)
valentin-deschaintre/Guided_fine_tuning_SVBRDF/helpers.py
code served (permissive licence) · get_code("fac0ec37a83fedc7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 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.

FunctionAlso present inEarliest-datedOthers named
deprocess 5 other papers
5 dated earlier
1602.01783 (2016-02)
Asynchronous Methods for Deep Reinforcement Learning
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1810.09718 (2018-10)
Single-Image SVBRDF Capture with a Rendering-Aware Deep Network
and 2 more not named here
preprocess 5 other papers
5 dated earlier
1602.01783 (2016-02)
Asynchronous Methods for Deep Reinforcement Learning
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1810.09718 (2018-10)
Single-Image SVBRDF Capture with a Rendering-Aware Deep Network
and 2 more not named here
lrelu 3 other papers
3 dated earlier
1804.09337 (2018-04)
Learning a Discriminative Feature Network for Semantic Segmentation
1806.05376 (2018-06)
Single Image Reflection Separation with Perceptual Losses
1906.11557 (2019-06)
Flexible SVBRDF Capture with a Multi-Image Deep Network
defaultScene 1 other paper
1 dated earlier
1906.11557 (2019-06)
Flexible SVBRDF Capture with a Multi-Image Deep Network
l1 1 other paper
1 dated earlier
1906.11557 (2019-06)
Flexible SVBRDF Capture with a Multi-Image Deep Network
logTensor 1 other paper
1 dated earlier
1906.11557 (2019-06)
Flexible SVBRDF Capture with a Multi-Image Deep Network

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

We present a method to transfer the appearance of one or a few exemplar SVBRDFs to a target image representing similar materials. Our solution is extremely simple: we fine-tune a deep appearance-capture network on the provided exemplars, such that it learns to extract similar SVBRDF values from the target image. We introduce two novel material capture and design workflows that demonstrate the strength of this simple approach. Our first workflow allows to produce plausible SVBRDFs of large-scale objects from only a few pictures. Specifically, users only need take a single picture of a large surface and a few close-up flash pictures of some of its details. We use existing methods to extract SVBRDF parameters from the close-ups, and our method to transfer these parameters to the entire surface, enabling the lightweight capture of surfaces several meters wide such as murals, floors and furniture. In our second workflow, we provide a powerful way for users to create large SVBRDFs from internet pictures by transferring the appearance of existing, pre-designed SVBRDFs. By selecting different exemplars, users can control the materials assigned to the target image, greatly enhancing the creative possibilities offered by deep appearance capture.

For agents

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

get_harvested_code_for_paper("2007.03059")
get_code_for_paper("2007.03059")
have("2007.03059")

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

curl https://syntology.ai/api/ran/2007.03059.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.03059.svg)](https://syntology.ai/paper/2007.03059)

Connect an agent — have() is free.