SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.11418 · 2021

Layered Neural Atlases for Consistent Video Editing

arXiv · PDF · Open in the Atlas

Code that ran

13 of 17 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, 0 violated it and 11 have no contract verdict; 1 failure of our instrument; 4 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/2109.11418.json · badge: /api/ran/2109.11418.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
ykasten/layered-neural-atlases community (classifier label)
classifier basis not recorded on the link
7 ran · 4 no recorded run
thiagoambiel/NeuralAtlases community (classifier label)
classifier basis not recorded on the link
6 ran · 0 no recorded run
FunctionStatusWhere it lives
compute_consistency Ran
ran on a synthesized input
ykasten/layered-neural-atlases/unwrap_utils.py
code served (permissive licence) · get_code("25aa1f949b3ee275")
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 numpy as np
import cv2

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

# Create small test optical flow fields
# flow12 and flow21 should be (H, W, 2) arrays where the last dimension contains (dx, dy)
height, width = 4, 3
flow12 = np.random.randn(height, width, 2).astype(np.float32) * 0.5
flow21 = np.random.randn(height, width, 2).astype(np.float32) * 0.5

ARGS = {
    "flow12": flow12,
    "flow21": flow21,
}
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 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
count_parameters Ran
ran, honoured the contract we drafted
ykasten/layered-neural-atlases/implicit_neural_networks.py
code served (permissive licence) · get_code("f6b944f50d3f15ae")
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) 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 torch
import torch.nn as nn

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        x = self.linear1(x)
        x = self.linear2(x)
        return x

model = SimpleModel()

ARGS = {
    "model": model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — 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
get_colors Ran
ran on a synthesized input
ykasten/layered-neural-atlases/evaluate.py
code served (permissive licence) · get_code("b517b213dc8155a1")
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 torch
import numpy as np

torch.manual_seed(0)

# Create a small image (height=10, width=10, channels=3)
image = torch.rand(10, 10, 3)

# Create small point coordinate tensors
pointx = torch.tensor([2.5, 7.3])
pointy = torch.tensor([3.1, 8.9])

# Define coordinate bounds and resolution
resolution = 100
minx = 0.0
maxx = 10.0
miny = 0.0
maxy = 10.0

ARGS = {
    'resolution': resolution,
    'minx': minx,
    'maxx': maxx,
    'miny': miny,
    'maxy': maxy,
    'pointx': pointx,
    'pointy': pointy,
    'image': image
}
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 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_consistency_mask Ran
ran on a synthesized input
ykasten/layered-neural-atlases/unwrap_utils.py
code served (permissive licence) · get_code("c19aa5a284101d2d")
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, 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 torch
import numpy as np

torch.manual_seed(0)

# Create small optical flow tensors
# Shape: (height, width, 2) where 2 represents (flow_x, flow_y)
height, width = 4, 5
optical_flow = torch.randn(height, width, 2, dtype=torch.float32)
optical_flow_reverse = torch.randn(height, width, 2, dtype=torch.float32)

ARGS = {
    "optical_flow": optical_flow,
    "optical_flow_reverse": optical_flow_reverse,
}
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 tuple, ndim 3, 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
interpolate_alpha Ran
ran on a synthesized input
ykasten/layered-neural-atlases/evaluate.py
code served (permissive licence) · get_code("a240f3b65e0dfa51")
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 (1000, 1000) 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

# Analyze the function:
# - m1_alpha_u, m1_alpha_v, m1_alpha_alpha are concatenated (so they're lists/tuples of arrays)
# - After concatenation, they're passed to griddata as coordinate arrays and values
# - griddata expects (x, y) coordinates and corresponding values
# - The result is interpolated on a 1000x1000 grid

# Create small sample data
# These should be lists of arrays that will be concatenated
m1_alpha_u = [np.array([10.5, 20.3, 30.1]), np.array([50.2, 60.8])]
m1_alpha_v = [np.array([15.3, 25.1, 35.9]), np.array([55.4, 65.2])]
m1_alpha_alpha = [np.array([0.1, 0.5, 0.3]), np.array([0.7, 0.2])]

ARGS = {
    "m1_alpha_v": m1_alpha_v,
    "m1_alpha_u": m1_alpha_u,
    "m1_alpha_alpha": m1_alpha_alpha,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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 (1000, 1000) — shape (1000, 1000) 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
positionalEncoding_vec Ran
ran; our contract draft was wrong, not the code
ykasten/layered-neural-atlases/implicit_neural_networks.py
code served (permissive licence) · get_code("ab6aff4b59ac84d5")
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 Tensor, ndim 2, dtype family float, shape (2, 24) 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

torch.manual_seed(0)

# Analyze the function:
# - in_tensor is used in einsum 'ij, k -> ijk', so it needs shape (i, j)
# - b is used in einsum 'ij, k -> ijk', so it needs shape (k,)
# - The function performs einsum, then cat on dim=1, transpose, view operations
# - All operations are tensor operations, no special methods needed

in_tensor = torch.randn(2, 3)  # batch_size=2, feature_dim=3
b = torch.randn(4)  # projection_dim=4

ARGS = {
    'in_tensor': in_tensor,
    'b': b
}
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 Tensor, ndim 2, dtype family float, shape (2, 24) — shape (2, 24) 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
read_atlas Ran
ran on a synthesized input
thiagoambiel/NeuralAtlases/core/utils.py
code served (permissive licence) · get_code("a10bae5354360048")
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 Tensor, ndim 4, dtype family float, shape (2, 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 os
from pathlib import Path
import tempfile
import numpy as np
import torch
import cv2

torch.manual_seed(0)

# Create a temporary directory with a test image
temp_dir = tempfile.TemporaryDirectory()
temp_path = Path(temp_dir.name)

# Create a simple test image file
test_image_array = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
test_image_path = temp_path / "test_image.png"
cv2.imwrite(str(test_image_path), test_image_array)

# Test case 1: Single image file path
single_image_path = str(test_image_path)

# Test case 2: Directory with multiple image files
atlas_dir = temp_path / "atlas"
atlas_dir.mkdir(exist_ok=True)
for i in range(2):
    img_array = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
    img_path = atlas_dir / f"frame_{i}.png"
    cv2.imwrite(str(img_path), img_array)

ARGS = {
    "path": atlas_dir
}
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 Tensor, ndim 4, dtype family float, shape (2, 4, 3, 3) — shape (2, 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
read_image Ran
ran on a synthesized input
thiagoambiel/NeuralAtlases/core/utils.py
code served (permissive licence) · get_code("19927e7f348ee165")
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 (100, 100, 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 os
import cv2
import numpy as np
import torch
from pathlib import Path
import tempfile

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

# Create a small test image (100x100 RGB)
test_image = np.random.randint(0, 256, (100, 100, 3), dtype=np.uint8)
cv2.imwrite(temp_image_path, test_image)

ARGS = {
    "image_path": temp_image_path,
    "normalize": True,
    "as_tensor": False,
}
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 3, dtype family float, shape (100, 100, 3) — shape (100, 100, 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
resize_flow Ran
ran on a synthesized input
thiagoambiel/NeuralAtlases/core/utils.py
code served (permissive licence) · get_code("0b08aabb315885e3")
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 (8, 10, 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 cv2
import numpy as np

# Create a small optical flow array
# Optical flow arrays have shape (height, width, 2) where the last dimension contains (dx, dy)
old_h, old_w = 4, 5
flow = np.random.randn(old_h, old_w, 2).astype(np.float32)

# Define new dimensions
new_h = 8
new_w = 10

ARGS = {
    "flow": flow,
    "new_h": new_h,
    "new_w": new_w,
}
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 float, shape (8, 10, 2) — shape (8, 10, 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
squared_euclidean_norm Ran
ran on a synthesized input
thiagoambiel/NeuralAtlases/core/norms.py
code served (permissive licence) · get_code("d7946517af608ccf")
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 Tensor, 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

torch.manual_seed(0)

# Create a small tensor with shape (batch_size=2, features=4)
# The function uses .pow(2).sum(dim=1), so it expects a 2D tensor
# and will sum along dimension 1 (across features)
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 Tensor, ndim 1, dtype family float — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
squared_taxicab_norm Ran
ran on a synthesized input
thiagoambiel/NeuralAtlases/core/norms.py
code served (permissive licence) · get_code("dc4e34290b9bd09b")
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 Tensor, 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

torch.manual_seed(0)

# Create a small tensor with batch size 2 and dimension 4
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 Tensor, ndim 1, dtype family float — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
taxicab_norm Ran
ran on a synthesized input
thiagoambiel/NeuralAtlases/core/norms.py
code served (permissive licence) · get_code("cf36cb0ed2371553")
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 Tensor, 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

torch.manual_seed(0)

# Create a small tensor with shape (batch_size=2, features=4)
# The function computes taxicab norm along dim=1, so we need at least 2 dimensions
x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 Tensor, ndim 1, dtype family float — no output shape is stated: observe_signature.py could not observe it (import:OSError)
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
warp_flow Ran
ran on a synthesized input
ykasten/layered-neural-atlases/unwrap_utils.py
code served (permissive licence) · get_code("39530fbf3996794c")
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 (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 cv2

# Create a small test image (height=4, width=3, channels=3)
# Using uint8 as typical for cv2 operations
img = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)

# Create a flow field (height=4, width=3, 2 channels for x,y displacement)
# Using float32 as typical for optical flow
flow = np.random.randn(4, 3, 2).astype(np.float32)

ARGS = {
    "img": img,
    "flow": flow,
}
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 (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
bilinear_interpolate_numpy Not yet run
unverified (harvested, no recorded run)
ykasten/layered-neural-atlases/evaluate.py
pointer only (licence: MIT); the stored copy get_code serves, from Chris-lange/SDM_active_sampling, is pointer only (licence: NONE) · get_code("e1f29854df55ad3e")
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 Chris-lange/SDM_active_sampling, 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. No invocation recorded.

get_gradient_loss Not yet run
unverified (harvested, no recorded run)
ykasten/layered-neural-atlases/loss_utils.py
code served (permissive licence) · get_code("367ba68aacda929c")
How it ran

no invocation recorded.

get_optical_flow_loss_all Not yet run
unverified (harvested, no recorded run)
ykasten/layered-neural-atlases/loss_utils.py
code served (permissive licence) · get_code("38ddfbd322efb739")
How it ran

no invocation recorded.

get_rigidity_loss Not yet run
unverified (harvested, no recorded run)
ykasten/layered-neural-atlases/loss_utils.py
code served (permissive licence) · get_code("3982f2b00a240333")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 3 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 3 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
count_parameters 180 other papers
44 dated earlier, 2 the same month, 134 later · 8 only as an assembly brick
1705.08415 (2017-05)
Supervised Community Detection with Line Graph Neural Networks
1707.01926 (2017-07)
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
1808.09367 (2018-08)
Deriving Machine Attention from Human Rationales
and 177 more not named here
positionalEncoding_vec 3 other papers
3 later
2204.02491 (2022-04)
Text2LIVE: Text-Driven Layered Image and Video Editing
2303.08120 (2023-03)
Blind Video Deflickering by Neural Filtering with a Flawed Atlas
2308.09592 (2023-08)
StableVideo: Text-driven Consistency-aware Diffusion Video Editing
bilinear_interpolate_numpy 2 other papers
2 later
2311.02061 (2023-11)
Active Learning-Based Species Range Estimation

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 that decomposes, or "unwraps", an input video into a set of layered 2D atlases, each providing a unified representation of the appearance of an object (or background) over the video. For each pixel in the video, our method estimates its corresponding 2D coordinate in each of the atlases, giving us a consistent parameterization of the video, along with an associated alpha (opacity) value. Importantly, we design our atlases to be interpretable and semantic, which facilitates easy and intuitive editing in the atlas domain, with minimal manual work required. Edits applied to a single 2D atlas (or input video frame) are automatically and consistently mapped back to the original video frames, while preserving occlusions, deformation, and other complex scene effects such as shadows and reflections. Our method employs a coordinate-based Multilayer Perceptron (MLP) representation for mappings, atlases, and alphas, which are jointly optimized on a per-video basis, using a combination of video reconstruction and regularization losses. By operating purely in 2D, our method does not require any prior 3D knowledge about scene geometry or camera poses, and can handle complex dynamic real world videos. We demonstrate various video editing applications, including texture mapping, video style transfer, image-to-video texture transfer, and segmentation/labeling propagation, all automatically produced by editing a single 2D atlas image.

For agents

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

get_harvested_code_for_paper("2109.11418")
get_code_for_paper("2109.11418")
have("2109.11418")

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

curl https://syntology.ai/api/ran/2109.11418.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.11418.svg)](https://syntology.ai/paper/2109.11418)

Connect an agent — have() is free.