SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.00867 · CVPR · 2022

Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding

Yanwei Fu, Qiaole Dong, Chenjie Cao

arXiv · PDF · Open in the Atlas

Code that ran

12 of 16 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (2 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 8 have no contract verdict; 2 failures 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/2203.00867.json · badge: /api/ran/2203.00867.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
DQiaole/ZITS_inpainting community
Papers with Code archive
6 ran · 3 no recorded run
dqiaole/zits community (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
FunctionStatusWhere it lives
CausalSelfAttention Ran
ran on a synthesized input
DQiaole/ZITS_inpainting/src/models/TSR_model.py
code served (permissive licence) · get_code("374b0040c780395d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, 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 torch.nn as nn

class Config:
    def __init__(self):
        self.n_embd = 8
        self.n_head = 2
        self.block_size = 5
        self.attn_pdrop = 0.1
        self.resid_pdrop = 0.1

config = Config()

INIT_ARGS = {
    'config': config
}

# Create input tensor with shape (batch_size, sequence_length, n_embd)
# batch_size = 2, sequence_length = 3, n_embd = 8
x = torch.randn(2, 3, 8)

ARGS = {
    'x': x,
    'layer_past': None
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 3, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
GELU Ran
ran on a synthesized input
DQiaole/ZITS_inpainting/src/models/TSR_model.py
code served (permissive licence) · get_code("c088eb9584bb3903")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, 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 math

def gelu(x):
    """Implementation of the gelu activation function.
        For information: OpenAI GPT's gelu is slightly different (and gives slightly different results):
        0.5 * x * (1 + torch.tanh(math.sqrt(2 / math.pi) * (x + 0.044715 * torch.pow(x, 3))))
    """
    return x * 0.5 * (1.0 + torch.erf(x / math.sqrt(2.0)))

class GELU(nn.Module):

    def __init__(self):
        super().__init__()

    def forward(self, x):
        return gelu(x)

INIT_ARGS = {}

ARGS = {
    'x': torch.randn(2, 5)
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
GELU2 Ran
ran on a synthesized input
DQiaole/ZITS_inpainting/src/models/TSR_model.py
code served (permissive licence) · get_code("0dcf0903f8538d11")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 2, 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

INIT_ARGS = {}

ARGS = {
    'x': torch.randn(2, 4)
}
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
SampleEdgeLineLogits Ran
ran on a synthesized input
dqiaole/zits/src/utils.py
code served (permissive licence) · get_code("42c0844d8edaf70f")
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 5, dtype family float; no output shape is stated. 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 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

torch.manual_seed(0)

class MockModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 4)
    
    def forward_with_logits(self, img, edge, line, masks):
        # img, edge, line all have shape (batch, channels, height, width)
        # Return edge_logits and line_logits with same shape
        batch_size = img.shape[0]
        height = img.shape[2]
        width = img.shape[3]
        
        edge_logits = torch.randn(batch_size, 1, height, width, dtype=torch.float16)
        line_logits = torch.randn(batch_size, 1, height, width, dtype=torch.float16)
        
        return edge_logits, line_logits

model = MockModel()

# Create context: [img, edge, line]
# Each should be (batch=2, channels=1, height=4, width=3)
img = torch.randn(2, 1, 4, 3)
edge = torch.zeros(2, 1, 4, 3)
line = torch.zeros(2, 1, 4, 3)
context = [img, edge, line]

# Create mask: (batch=2, channels=1, height=4, width=3)
# 1 means masked (to be inpainted), 0 means known
mask = torch.ones(2, 1, 4, 3)
mask[:, :, :2, :2] = 1  # Some pixels are masked

ARGS = {
    'model': model,
    'context': context,
    'mask': mask,
    'iterations': 1,
    'device': 'cpu',
    'add_v': 0,
    'mul_v': 4
}
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, ndim 5, 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
SelfAttention Ran
ran on a synthesized input · constructed an object; no result was computed
DQiaole/ZITS_inpainting/src/models/TSR_model.py
code served (permissive licence) · get_code("96c2a9a4d1843cec")
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 an instance of its own class, SelfAttention: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
import math

torch.manual_seed(0)

ARGS = {
    'n_embd': 4,
    'n_head': 2,
    'attn_pdrop': 0.1,
    'resid_pdrop': 0.1,
}
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 SelfAttention — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SelfAttention 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
calculate_activation_statistics Ran
ran; our contract draft was wrong, not the code
dqiaole/zits/src/inpainting_metrics.py
code served (permissive licence) · get_code("1c2fb75a32c87a57")
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 numpy as np
import torch
import torch.nn as nn
from torch.autograd import Variable

torch.manual_seed(0)

class SimpleInceptionModel(nn.Module):
    """Minimal inception-like model that returns a tensor with spatial dimensions."""
    def __init__(self):
        super(SimpleInceptionModel, self).__init__()
        self.conv1 = nn.Conv2d(3, 4, kernel_size=3, padding=1)
        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
    
    def forward(self, x):
        x = self.conv1(x)
        x = self.avgpool(x)
        return (x,)

model = SimpleInceptionModel()
model.eval()

images = np.random.rand(6, 3, 8, 8).astype(np.float32)

ARGS = {
    "images": images,
    "model": model,
    "batch_size": 2,
    "dims": 4,
    "cuda": False,
    "verbose": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, tqdm — 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
calculate_frechet_distance Ran
ran, violated the contract we drafted
dqiaole/zits/src/inpainting_metrics.py
code served (permissive licence) · get_code("d059051e90165ebe")
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 float32, 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 numpy as np
from scipy import linalg

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

# Create small sample statistics for Frechet Distance calculation
# mu1 and mu2 are mean vectors (1D arrays)
# sigma1 and sigma2 are covariance matrices (2D arrays)

dim = 4  # Feature dimension

# Generate mean vectors
mu1 = np.random.randn(dim).astype(np.float32)
mu2 = np.random.randn(dim).astype(np.float32)

# Generate positive semi-definite covariance matrices
# Create them as A @ A.T to ensure they're positive semi-definite
A1 = np.random.randn(dim, dim).astype(np.float32)
sigma1 = (A1 @ A1.T).astype(np.float32)

A2 = np.random.randn(dim, dim).astype(np.float32)
sigma2 = (A2 @ A2.T).astype(np.float32)

eps = 1e-06

ARGS = {
    'mu1': mu1,
    'sigma1': sigma1,
    'mu2': mu2,
    'sigma2': sigma2,
    'eps': eps
}
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 float32, 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
create_mask Ran
ran on a synthesized input
dqiaole/zits/src/utils.py
code served (permissive licence) · get_code("817b9a0ad441fb50")
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 (80, 100) 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 random
import numpy as np

random.seed(0)
np.random.seed(0)

ARGS = {
    "width": 100,
    "height": 80,
    "mask_width": 20,
    "mask_height": 15,
    "x": 10,
    "y": 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 ndarray, ndim 2, dtype family float, shape (80, 100) — shape (80, 100) 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
gelu Ran
ran, honoured the contract we drafted
DQiaole/ZITS_inpainting/src/models/TSR_model.py
code served (permissive licence) · get_code("50e1ffed03f484ec")
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 Tensor, 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 torch
import math

torch.manual_seed(0)

# The gelu function takes a single parameter 'x' which should be a tensor
# The function applies element-wise operations: multiplication, addition, torch.erf, and division
# So x should be a tensor that supports these operations

x = torch.randn(2, 4)

ARGS = {
    "x": x
}
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 Tensor, 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
get_activations Ran
ran; our contract draft was wrong, not the code
dqiaole/zits/src/inpainting_metrics.py
code served (permissive licence) · get_code("18bfc140d0a26202")
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 (8, 2048) as a later run recorded it. 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, 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
import numpy as np

torch.manual_seed(0)

class MockInceptionModel(nn.Module):
    def __init__(self):
        super(MockInceptionModel, self).__init__()
        self.fc = nn.Linear(2048, 2048)
    
    def forward(self, x):
        # Input: (batch_size, 3, height, width)
        # Output: (batch_size, 2048, spatial_h, spatial_w)
        batch_size = x.shape[0]
        # Return a tuple where first element is the feature tensor
        output = torch.randn(batch_size, 2048, 4, 5)
        return (output,)

# Create mock images: (n_images, 3, height, width) with values between 0 and 1
images = np.random.rand(8, 3, 32, 32).astype(np.float32)

# Create the model
model = MockInceptionModel()

ARGS = {
    'images': images,
    'model': model,
    'batch_size': 2,
    'dims': 2048,
    'cuda': False,
    'verbose': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, tqdm — 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 (8, 2048) — shape (8, 2048) 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
my_Block_2 Ran
ran on a synthesized input · constructed an object; no result was computed
DQiaole/ZITS_inpainting/src/models/TSR_model.py
code served (permissive licence) · get_code("5db9dac361c10f1f")
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 an instance of its own class, my_Block_2: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn
import math

torch.manual_seed(0)

class Config:
    def __init__(self):
        self.n_embd = 4
        self.n_head = 2
        self.block_size = 8
        self.attn_pdrop = 0.1
        self.resid_pdrop = 0.1

config = Config()

ARGS = {
    "config": config
}
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 my_Block_2 — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a my_Block_2 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
to_int Ran
ran on a synthesized input
dqiaole/zits/datasets/dataset_FTR.py
code served (permissive licence) · get_code("bad108729054f08a")
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 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

torch.manual_seed(0)

# The function to_int takes a parameter x and maps int() over it,
# then returns a tuple. So x should be an iterable of values that can be converted to int.
# This could be a list, tuple, numpy array, or tensor of numeric values.

x = [1.5, 2.7, 3.2, 4.9]

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 tuple, ndim 1, dtype family int — 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
AxialAttention Not yet run
unverified (harvested, no recorded run)
DQiaole/ZITS_inpainting/src/models/TSR_model.py
code served (permissive licence) · get_code("79e5b2a4b67a561a")
How it ran

no invocation recorded.

BlockAxial Not yet run
unverified (harvested, no recorded run)
DQiaole/ZITS_inpainting/src/models/TSR_model.py
code served (permissive licence) · get_code("fba8e898c2b6bfd4")
How it ran

no invocation recorded.

EdgeLineGPT256RelBCE Not yet run
unverified (harvested, no recorded run)
DQiaole/ZITS_inpainting/src/models/TSR_model.py
code served (permissive licence) · get_code("cdf9104f2e54ae72")
How it ran

no invocation recorded.

stitch_images Not yet run
unverified (harvested, no recorded run)
dqiaole/zits/src/utils.py
code served (permissive licence) · get_code("9ff337bc4bf82da5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 1 the same month, 4 later) and 9 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
gelu
brick of this paper's assembly: helper
198 other papers
101 dated earlier, 10 the same month, 83 later, 4 same year, order not determinable · 32 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.10125 (2019-01)
Glyce: Glyph-vectors for Chinese Character Representations
and 195 more not named here
calculate_activation_statistics 5 other papers
2 dated earlier, 3 later
Guo_Painting_From_Part_ICCV_2021_paper (2021 (year only))
Painting from Part
2103.15087 (2021-03)
Learning a Sketch Tensor Space for Image Inpainting of Man-made Scenes
2210.05950 (2022-10)
ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors
and 2 more not named here
calculate_frechet_distance 3 other papers
2 dated earlier, 1 later
2103.15087 (2021-03)
Learning a Sketch Tensor Space for Image Inpainting of Man-made Scenes
2108.08020 (2021-08)
Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates
2210.05950 (2022-10)
ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors
get_activations 2 other papers
1 dated earlier, 1 later
2103.15087 (2021-03)
Learning a Sketch Tensor Space for Image Inpainting of Man-made Scenes
2210.05950 (2022-10)
ZITS++: Image Inpainting by Improving the Incremental Transformer on Structural Priors
GELU
brick of this paper's assembly: helper
1 other paper
1 dated earlier
2109.06480 (2021-09)
Logic-level Evidence Retrieval and Graph-based Verification Network for Table-based Fact Verification
create_mask 1 other paper
1 dated earlier
1908.00463 (2019-08)
DIODE: A Dense Indoor and Outdoor DEpth Dataset
stitch_images 1 other paper
1 dated earlier
1908.00463 (2019-08)
DIODE: A Dense Indoor and Outdoor DEpth Dataset

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

Image inpainting has made significant advances in recent years. However, it is still challenging to recover corrupted images with both vivid textures and reasonable structures. Some specific methods only tackle regular textures while losing holistic structures due to the limited receptive fields of convolutional neural networks (CNNs). On the other hand, attention-based models can learn better long-range dependency for the structure recovery, but they are limited by the heavy computation for inference with large image sizes. To address these issues, we propose to leverage an additional structure restorer to facilitate the image inpainting incrementally. The proposed model restores holistic image structures with a powerful attentionbased transformer model in a fixed low-resolution sketch space. Such a grayscale space is easy to be upsampled to larger scales to convey correct structural information. Our structure restorer can be integrated with other pretrained inpainting models efficiently with the zero-initialized residual addition. Furthermore, a masking positional encoding strategy is utilized to improve the performance with large irregular masks. Extensive experiments on various datasets validate the efficacy of our model compared with other competitors. Our codes are released in https: //github.com/DQiaole/ZITS_inpainting.

For agents

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

get_harvested_code_for_paper("2203.00867")
get_code_for_paper("2203.00867")
have("2203.00867")

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

curl https://syntology.ai/api/ran/2203.00867.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.00867.svg)](https://syntology.ai/paper/2203.00867)

Connect an agent — have() is free.