SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.00803 · 2020

Lagrangian Neural Style Transfer for Fluids

arXiv · PDF · Open in the Atlas

Code that ran

6 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; 1 failure of our instrument; 1 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/2005.00803.json · badge: /api/ran/2005.00803.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
byungsook/neural-flow-style canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
add_argument_group Ran
ran; our contract draft was wrong, not the code
byungsook/neural-flow-style/config.py
code served (permissive licence) · get_code("6d80592fd6d47b2d")
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 _ArgumentGroup. 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 argparse

arg_lists = []
parser = argparse.ArgumentParser()

def add_argument_group(name):
    arg = parser.add_argument_group(name)
    arg_lists.append(arg)
    return arg

ARGS = {
    'name': 'test_group'
}
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 _ArgumentGroup — a _ArgumentGroup output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a _ArgumentGroup 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
batch_mgrid Ran
ran on a synthesized input
byungsook/neural-flow-style/transform.py
code served (permissive licence) · get_code("f4d50cb6c1ed76ce")
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, 0) 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

ARGS = {
    'n_batch': 2,
    'args': (4, 3),
    'low': -1.0,
    'high': 1.0,
}
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 EagerTensor, ndim 2, dtype family float, shape (2, 0) — shape (2, 0) 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
batch_warp2d Ran
ran on a synthesized input
byungsook/neural-flow-style/transform.py
code served (permissive licence) · get_code("3ffb1a3057ee059b")
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, 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

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

# Create tiny test tensors
n_batch = 2
xlen = 4
ylen = 3
n_channel = 2

# imgs: [n_batch, xlen, ylen, n_channel]
# Create a small image tensor with distinct dimension sizes
imgs = tf.constant(
    np.random.randn(n_batch, xlen, ylen, n_channel).astype(np.float32)
)

# mappings: [n_batch, xlen, ylen, 2]
# Contains x,y coordinate mappings normalized to [-1, 1]
mappings = tf.constant(
    np.random.uniform(-1, 1, (n_batch, xlen, ylen, 2)).astype(np.float32)
)

# sample_shape: [n_batch, xlen_, ylen_]
# Specifies the output spatial dimensions
sample_shape = [n_batch, xlen, ylen]

ARGS = {
    "imgs": imgs,
    "mappings": mappings,
    "sample_shape": sample_shape,
}
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, 2) — shape (2, 4, 3, 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
batch_warp3d Ran
ran on a synthesized input
byungsook/neural-flow-style/transform.py
code served (permissive licence) · get_code("f1f9fab15177e9c1")
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 5, dtype family float, shape (2, 4, 5, 6, 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

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

# Create small test tensors
n_batch = 2
xlen = 4
ylen = 5
zlen = 6
n_channel = 3

# imgs: [n_batch, xlen, ylen, zlen, n_channel]
imgs = tf.constant(
    np.random.randn(n_batch, xlen, ylen, zlen, n_channel).astype(np.float32)
)

# mappings: [n_batch, 3, xlen, ylen, zlen]
# Contains x, y, z coordinate mappings normalized to [-1, 1]
mappings = tf.constant(
    np.random.uniform(-1, 1, (n_batch, 3, xlen, ylen, zlen)).astype(np.float32)
)

# sample_shape: [n_batch, xlen, ylen, zlen]
sample_shape = tf.constant([n_batch, xlen, ylen, zlen], dtype=tf.int32)

ARGS = {
    "imgs": imgs,
    "mappings": mappings,
    "sample_shape": sample_shape,
}
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 5, dtype family float, shape (2, 4, 5, 6, 3) — shape (2, 4, 5, 6, 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
cosine_decay Ran
ran on a synthesized input
byungsook/neural-flow-style/util.py
code served (permissive licence) · get_code("322a47ff858b43d8")
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

ARGS = {
    "global_step": 100,
    "decay_steps": 1000,
    "learning_rate": 0.1,
    "factor": 0.5
}
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
repeat Ran
ran on a synthesized input
byungsook/neural-flow-style/vgg.py
code served (permissive licence) · get_code("66ce8a101ba12962")
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 tensorflow as tf
import numpy as np
from collections import OrderedDict

# Create a simple layer function that accepts outputs and additional arguments
def simple_layer(inputs, scope=None, **kwargs):
    """A simple layer that applies a basic transformation"""
    # This layer should accept inputs, scope, and any other kwargs
    # and return a tensor
    return inputs + 1.0

# Create test inputs - small tensor with batch=2, features=4
inputs_tensor = tf.constant(np.random.randn(2, 4).astype(np.float32))

# Number of repetitions
repetitions = 3

# The layer to repeat
layer = simple_layer

# Additional positional arguments for the layer (if any)
layer_args = ()

# Additional keyword arguments for the layer
layer_kwargs = {
    'some_param': 0.5
}

ARGS = {
    'inputs': inputs_tensor,
    'repetitions': repetitions,
    'layer': layer,
    'args': layer_args,
    'kwargs': layer_kwargs
}
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 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
preprocess Not yet run
unverified (harvested, no recorded run)
byungsook/neural-flow-style/vgg.py
code served (permissive licence) · get_code("5b0f602e36ba36f2")
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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 6 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
add_argument_group 27 other papers
15 dated earlier, 12 later
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1506.03134 (2015-06)
Pointer Networks
1609.04802 (2016-09)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
and 24 more not named here

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

Artistically controlling the shape, motion and appearance of fluid simulations pose major challenges in visual effects production. In this paper, we present a neural style transfer approach from images to 3D fluids formulated in a Lagrangian viewpoint. Using particles for style transfer has unique benefits compared to grid-based techniques. Attributes are stored on the particles and hence are trivially transported by the particle motion. This intrinsically ensures temporal consistency of the optimized stylized structure and notably improves the resulting quality. Simultaneously, the expensive, recursive alignment of stylization velocity fields of grid approaches is unnecessary, reducing the computation time to less than an hour and rendering neural flow stylization practical in production settings. Moreover, the Lagrangian representation improves artistic control as it allows for multi-fluid stylization and consistent color transfer from images, and the generality of the method enables stylization of smoke and liquids likewise.

For agents

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

get_harvested_code_for_paper("2005.00803")
get_code_for_paper("2005.00803")
have("2005.00803")

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

curl https://syntology.ai/api/ran/2005.00803.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.00803.svg)](https://syntology.ai/paper/2005.00803)

Connect an agent — have() is free.