SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 136670327 · ECCV · 2022

Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization

Jue Wang, Chi-Man Pun, Xiaodong Cun, Jingtang Liang

Open in the Atlas

Code that ran

14 of 20 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; 2 honoured the contract we drafted, 0 violated it and 11 have no contract verdict; 1 failure of our instrument; 6 no recorded run), measured 2026-11-22; 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/136670327.json · badge: /api/ran/136670327.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
stefanLeong/S2CRNet canonical (classifier label)
classifier basis: census
14 ran · 6 no recorded run
FunctionStatusWhere it lives
color_normalize Ran
ran on a synthesized input
stefanLeong/S2CRNet/utils/transforms.py
code served (permissive licence) · get_code("27883379b352ff78")
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 3, dtype family float, shape (3, 4, 5) 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 numpy as np

torch.manual_seed(0)

# The function color_normalize expects:
# x: a tensor with shape (C, H, W) where C is channels
# mean: iterable of mean values (one per channel)
# std: iterable of std values (one per channel)

# Create a small tensor with shape (3, 4, 5) - 3 channels, 4x5 spatial dims
x = torch.randn(3, 4, 5)

# Create mean and std as lists/tensors with 3 values (one per channel)
mean = [0.5, 0.4, 0.3]
std = [0.2, 0.25, 0.15]

ARGS = {
    "x": x,
    "mean": mean,
    "std": std
}
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 Tensor, ndim 3, dtype family float, shape (3, 4, 5) — shape (3, 4, 5) 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
dist_acc Ran
ran on a synthesized input
stefanLeong/S2CRNet/utils/evaluation.py
code served (permissive licence) · get_code("595dd61b55bc5d01")
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 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 torch

torch.manual_seed(0)

# Create a tensor of distances with some values below threshold, some above, and some -1 values
dists = torch.tensor([0.2, 0.7, -1.0, 0.3, 0.9, -1.0], dtype=torch.float32)

ARGS = {
    "dists": dists,
    "thr": 0.5
}
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 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
flip_back Ran
ran on a synthesized input
stefanLeong/S2CRNet/utils/transforms.py
code served (permissive licence) · get_code("65686ab32ac3221a")
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, 16, 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 torch

torch.manual_seed(0)

# Create a small 4D tensor (batch_size=2, channels=16, height=4, width=3)
# This represents heatmaps with 16 keypoints for a batch of 2 images
flip_output_tensor = torch.randn(2, 16, 4, 3).float()

ARGS = {
    'flip_output': flip_output_tensor,
    'dataset': 'mpii'
}
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 Tensor, ndim 4, dtype family float, shape (2, 16, 4, 3) — shape (2, 16, 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
gram_matrix Ran
ran on a synthesized input
stefanLeong/S2CRNet/utils/losses.py
code served (permissive licence) · get_code("1715f300a6a58899")
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 3, dtype family float, shape (2, 4, 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

torch.manual_seed(0)

# Create a small feature tensor with shape (batch=2, channels=4, height=3, width=5)
# Using distinct sizes: batch=2, ch=4, h=3, w=5 to make dimensions unambiguous
feat = torch.randn(2, 4, 3, 5)

ARGS = {
    'feat': feat
}
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 3, dtype family float, shape (2, 4, 4) — shape (2, 4, 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
is_dic Ran
ran on a synthesized input
stefanLeong/S2CRNet/utils/losses.py
code served (permissive licence) · get_code("bde8d7f70effb0de")
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 bool, 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 torch

torch.manual_seed(0)

ARGS = {
    "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 bool, 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
is_dir Ran
ran on a synthesized input
stefanLeong/S2CRNet/utils/osutils.py
code served (permissive licence) · get_code("4593e986199e8e6d")
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 bool, 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 os
import tempfile

# Create a temporary directory to pass as an argument
temp_dir = tempfile.mkdtemp()

ARGS = {
    "dirname": temp_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 bool, 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
is_file Ran
ran on a synthesized input
stefanLeong/S2CRNet/utils/osutils.py
code served (permissive licence) · get_code("9cf3f7aa3f925fa3")
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 bool, 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 os
import tempfile

# Create a temporary file for testing
with tempfile.NamedTemporaryFile(delete=False) as tmp:
    tmp_path = tmp.name

try:
    ARGS = {
        "fname": tmp_path
    }
finally:
    # Clean up
    if os.path.exists(tmp_path):
        os.remove(tmp_path)
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 bool, 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
l1_relative Ran
ran on a synthesized input
stefanLeong/S2CRNet/utils/losses.py
code served (permissive licence) · get_code("497f8ba1f33581f8")
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 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 torch

torch.manual_seed(0)

# Create tensors for the function
# batch=2, spatial dimensions=4 (flattened to 4)
batch_size = 2
spatial_size = 4

# reconstructed: shape (batch, spatial)
reconstructed = torch.randn(batch_size, spatial_size)

# real: shape (batch, spatial)
real = torch.randn(batch_size, spatial_size)

# mask: shape (batch, spatial) with binary values
mask = torch.randint(0, 2, (batch_size, spatial_size)).float()

ARGS = {
    "reconstructed": reconstructed,
    "real": real,
    "mask": mask,
}
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 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
plot_overlap Ran
ran; our contract draft was wrong, not the code
stefanLeong/S2CRNet/utils/logger.py
code served (permissive licence) · get_code("921113cf2a16c965")
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 list, 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 numpy as np

class MockLogger:
    def __init__(self):
        self.title = "test_plot"
        self.names = ["loss", "accuracy", "f1_score"]
        self.numbers = {
            "loss": [0.5, 0.4, 0.3, 0.2],
            "accuracy": [0.6, 0.7, 0.8, 0.9],
            "f1_score": [0.55, 0.65, 0.75, 0.85]
        }

logger = MockLogger()

ARGS = {
    "logger": logger,
    "names": None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list 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
resize_to_match Ran
ran on a synthesized input
stefanLeong/S2CRNet/utils/misc.py
code served (permissive licence) · get_code("d16aaae5fd25013f")
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, 7, 9) 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.functional as F

torch.manual_seed(0)

# The function resizes fm to match the spatial dimensions of 'to'
# It uses: fm.size()[-2:] to get last 2 dimensions, to.size()[-2:] to get target spatial dims
# Both parameters should be tensors with at least 2 spatial dimensions

fm = torch.randn(2, 4, 3, 5)  # batch=2, channels=4, height=3, width=5
to = torch.randn(2, 4, 7, 9)  # batch=2, channels=4, height=7, width=9 (target spatial size)

ARGS = {
    'fm': fm,
    'to': to,
}
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 4, dtype family float, shape (2, 4, 7, 9) — shape (2, 4, 7, 9) 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
shufflelr Ran
ran on a synthesized input
stefanLeong/S2CRNet/utils/transforms.py
code served (permissive licence) · get_code("dfb09810607ef0cd")
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 (16, 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 torch

torch.manual_seed(0)

# x is a tensor of shape (num_keypoints, num_coords)
# The function indexes x[pair[0], :] and x[pair[1], :], so we need at least 16 rows (max index 15)
# Each row represents coordinates of a keypoint
x = torch.randn(16, 2)

# width is an integer representing image width
width = 256

# dataset is a string, should be 'mpii' based on the function logic
dataset = 'mpii'

ARGS = {
    'x': x,
    'width': width,
    'dataset': dataset
}
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 (16, 2) — shape (16, 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
tensor2img Ran
ran on a synthesized input
stefanLeong/S2CRNet/utils/imgUtils.py
code served (permissive licence) · get_code("f87ac6a63023d327")
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, 5, 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 torch
import numpy as np

torch.manual_seed(0)

# Create a small tensor in CHW format (channels, height, width)
# The function expects batched input [batch, channels, height, width]
# Values in range [-1, 1] based on the normalization in the function
input_tensor = torch.randn(1, 3, 4, 5)  # batch=1, channels=3, height=4, width=5

ARGS = {
    "input_image": input_tensor,
    "imtype": np.uint8
}
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 ndarray, ndim 3, dtype family int, shape (4, 5, 3) — shape (4, 5, 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
to_numpy Ran
ran, honoured the contract we drafted
stefanLeong/S2CRNet/utils/misc.py
pointer only (licence: MIT); the stored copy get_code serves, from SY-Xuan/IICS, is pointer only (licence: NONE) · get_code("b476623700945834")
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 SY-Xuan/IICS, 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. A run is recorded.

to_torch Ran
ran, honoured the contract we drafted
stefanLeong/S2CRNet/utils/misc.py
pointer only (licence: MIT); the stored copy get_code serves, from liu-xb/GCMT, is pointer only (licence: NONE) · get_code("7aac4c51e0ceee97")
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 liu-xb/GCMT, 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. A run is recorded.

calc_dists Not yet run
unverified (harvested, no recorded run)
stefanLeong/S2CRNet/utils/evaluation.py
code served (permissive licence) · get_code("e9fc00eea6f71c67")
How it ran

no invocation recorded.

get_preds Not yet run
unverified (harvested, no recorded run)
stefanLeong/S2CRNet/utils/evaluation.py
code served (permissive licence) · get_code("d9b53a2c9d1a3eb5")
How it ran

no invocation recorded.

im_to_numpy Not yet run
unverified (harvested, no recorded run)
stefanLeong/S2CRNet/utils/imgUtils.py
code served (permissive licence) · get_code("0f501bcb9a1fda50")
How it ran

no invocation recorded.

im_to_torch Not yet run
unverified (harvested, no recorded run)
stefanLeong/S2CRNet/utils/imgUtils.py
code served (permissive licence) · get_code("c98eeba8cbddf187")
How it ran

no invocation recorded.

join_path Not yet run
unverified (harvested, no recorded run)
stefanLeong/S2CRNet/utils/osutils.py
code served (permissive licence) · get_code("842ae91263089bd6")
How it ran

no invocation recorded.

patch_replication_callback Not yet run
unverified (harvested, no recorded run)
stefanLeong/S2CRNet/utils/parallel.py
code served (permissive licence) · get_code("e50200dbeffa0133")
How it ran

no invocation recorded.

Also present in other papers' code

Of 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 0 the same month, 5 later) and 13 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
plot_overlap 31 other papers
19 dated earlier, 11 later, 1 same year, order not determinable
1612.06321 (2016-12)
Large-Scale Image Retrieval with Attentive Deep Local Features
1805.07925 (2018-05)
Batch-Instance Normalization for Adaptively Style-Invariant Neural Networks
1806.04606 (2018-06)
Knowledge Distillation by On-the-Fly Native Ensemble
and 28 more not named here
patch_replication_callback 16 other papers
12 dated earlier, 1 later, 3 same year, order not determinable
1612.01105 (2016-12)
Pyramid Scene Parsing Network
1807.10221 (2018-07)
Unified Perceptual Parsing for Scene Understanding
1904.01941 (2019-04)
Character Region Awareness for Text Detection
and 13 more not named here
to_torch 9 other papers
6 dated earlier, 1 later, 2 same year, order not determinable · 3 only as an assembly brick
1912.08265 (2019-12)
Learning from Synthetic Animals
2003.02501 (2020-03)
Detecting Attended Visual Targets in Video
2007.09919 (2020-07)
Robust Tracking against Adversarial Attacks
and 6 more not named here
gram_matrix 6 other papers
6 dated earlier
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1804.07723 (2018-04)
Image Inpainting for Irregular Holes Using Partial Convolutions
2004.02788 (2020-04)
Self-Supervised Scene De-occlusion
and 3 more not named here
to_numpy 5 other papers
3 dated earlier, 1 later, 1 same year, order not determinable
2003.02501 (2020-03)
Detecting Attended Visual Targets in Video
2007.09919 (2020-07)
Robust Tracking against Adversarial Attacks
2103.11658 (2021-03)
Intra-Inter Camera Similarity for Unsupervised Person Re-Identification
and 2 more not named here
im_to_numpy 3 other papers
2 dated earlier, 1 later
1912.08265 (2019-12)
Learning from Synthetic Animals
2007.09919 (2020-07)
Robust Tracking against Adversarial Attacks
2308.09951 (2023-08)
Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos
im_to_torch 1 other paper
1 dated earlier
1912.08265 (2019-12)
Learning from Synthetic Animals

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 harmonization aims to modify the color of the composited region according to the specific background. Previous works model this task as a pixel-wise image translation using UNet family structures. However, the model size and computational cost limit the ability of their models on edge devices and higher-resolution images. In this paper, we propose spatial-separated curve rendering network (S 2 CRNet), a novel framework to prove that the simple global editing can effectively address this task as well as the challenge of high-resolution image harmonization for the first time. In S 2 CRNet, we design a curve rendering module (CRM) using spatial-specific knowledge to generate the parameters of the piece-wise curve mapping in the foreground region and we can directly render the original high-resolution images using the learned color curve. Besides, we also make two extensions of the proposed framework via cascaded refinement and semantic guidance. Experiments show that the proposed method reduces more than 90% parameters compared with previous methods but still achieves the state-of-the-art performance on 3 benchmark datasets. Moreover, our method can work smoothly on higher resolution images with much lower GPU computational resources. The source codes are available at: http: //github.com/stefanLeong/S2CRNet.

For agents

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

get_harvested_code_for_paper("136670327")
get_code_for_paper("136670327")
have("136670327")

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

curl https://syntology.ai/api/ran/136670327.json

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

[![Syntology run record](https://syntology.ai/api/ran/136670327.svg)](https://syntology.ai/paper/136670327)

Connect an agent — have() is free.