SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.09909 · 2019

Deep Exemplar-based Video Colorization

arXiv · PDF · Open in the Atlas

Code that ran

12 of 15 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 9 have no contract verdict; 2 failures of our instrument; 3 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/1906.09909.json · badge: /api/ran/1906.09909.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
zhangmozhe/video-colorization canonical (classifier label)
classifier basis: census
12 ran · 3 no recorded run
FunctionStatusWhere it lives
CustomFunc Ran
ran on a synthesized input
zhangmozhe/video-colorization/lib/TestTransforms.py
code served (permissive licence) · get_code("677fa59128ae0750")
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. 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

torch.manual_seed(0)

# Define a simple function that will be used as the `func` parameter
def simple_func(tensor, *args, **kwargs):
    """A simple function that processes tensors"""
    return tensor * 2

# Create small tensors for inputs
# inputs[0]: im_l
im_l = torch.randn(2, 4)

# inputs[1]: im_ab
im_ab = torch.randn(2, 4)

# inputs[2]: warp_ba
warp_ba = torch.randn(2, 4)

# inputs[3]: warp_aba
warp_aba = torch.randn(2, 4)

# inputs[4-8]: 5 layers, each containing [err_ba, err_ab]
layers = []
for _ in range(5):
    err_ba = torch.randn(2, 4)
    err_ab = torch.randn(2, 4)
    layers.append([err_ba, err_ab])

# Construct the inputs list
inputs = [im_l, im_ab, warp_ba, warp_aba] + layers

# Define additional args and kwargs that will be passed to func
additional_args = ()
additional_kwargs = {}

ARGS = {
    'inputs': inputs,
    'func': simple_func,
    'args': additional_args,
    'kwargs': additional_kwargs
}
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 list — a list 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
CustomFunc Ran
ran on a synthesized input
zhangmozhe/video-colorization/lib/TrainTransforms.py
code served (permissive licence) · get_code("a01afef2e16c2fdf")
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. 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

torch.manual_seed(0)

# Define a simple function that will be used as the `func` parameter
def simple_func(x, scale=1.0):
    return x * scale

# Create input tensors
# We need 6 base inputs + 5 layers, where each layer has 2 elements
im_l = torch.randn(2, 4)
im_ab = torch.randn(2, 4)
warp_ba = torch.randn(2, 4)
warp_aba = torch.randn(2, 4)
im_gbl_ab = torch.randn(2, 4)
bgr_mc_im = torch.randn(2, 4)

# Create 5 layers, each with 2 elements
layers = [
    [torch.randn(2, 4), torch.randn(2, 4)],
    [torch.randn(2, 4), torch.randn(2, 4)],
    [torch.randn(2, 4), torch.randn(2, 4)],
    [torch.randn(2, 4), torch.randn(2, 4)],
    [torch.randn(2, 4), torch.randn(2, 4)],
]

# Construct the inputs list
inputs = [im_l, im_ab, warp_ba, warp_aba, im_gbl_ab, bgr_mc_im] + layers

ARGS = {
    'inputs': inputs,
    'func': simple_func,
}
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 list — a list 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
batch_lab2rgb_transpose_mc Ran
ran on a synthesized input
zhangmozhe/video-colorization/lib/videoloader.py
code served (permissive licence) · get_code("631f17745747a7f0")
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 (8, 12, 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 batch L channel: (batch_size=2, channels=1, height=4, width=3)
img_l_mc = torch.randn(2, 1, 4, 3)

# Create batch AB channels: (batch_size=2, channels=2, height=4, width=3)
img_ab_mc = torch.randn(2, 2, 4, 3)

# nrow parameter for make_grid
nrow = 2

ARGS = {
    'img_l_mc': img_l_mc,
    'img_ab_mc': img_ab_mc,
    'nrow': nrow
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage, torch, torchvision — 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 (8, 12, 3) — shape (8, 12, 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
conv_to_relu Ran
ran on a synthesized input
zhangmozhe/video-colorization/lib/FeatVGG.py
code served (permissive licence) · get_code("c423f6909dca5643")
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 torch

def conv_to_relu(layer_names):
    out_layernames = []
    for name in layer_names:
        if name.startswith('conv'):
            out_layernames.append('relu' + name[4:])
        else:
            out_layernames.append(name)
    return out_layernames

ARGS = {
    'layer_names': ['conv1', 'batch_norm', 'conv2_3x3', 'dropout', 'conv_final']
}
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 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
find_local_patch Ran
ran on a synthesized input
zhangmozhe/video-colorization/models/NonlocalNet.py
code served (permissive licence) · get_code("a0126ccb4e3adacf")
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, 36, 3, 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 torch.nn.functional as F

torch.manual_seed(0)

# Create a small input tensor: (batch=2, channels=4, height=3, width=5)
x = torch.randn(2, 4, 3, 5)

# Define patch_size
patch_size = 3

ARGS = {
    "x": x,
    "patch_size": patch_size,
}
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, 36, 3, 5) — shape (2, 36, 3, 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
image_loader Ran
ran on a synthesized input
zhangmozhe/video-colorization/lib/videoloader_imagenet.py
code served (permissive licence) · get_code("a4acf74dd25fd887")
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 Image. 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 tempfile
import os
from PIL import Image

# Create a temporary directory and a simple test image
temp_dir = tempfile.mkdtemp()
image_path = os.path.join(temp_dir, "test_image.jpg")

# Create a simple RGB image and save it
test_image = Image.new('RGB', (4, 3), color=(255, 0, 0))
test_image.save(image_path)

ARGS = {
    "path": image_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
parse_images Ran
ran on a synthesized input
zhangmozhe/video-colorization/lib/videoloader.py
code served (permissive licence) · get_code("cc8ae9d282ba161a")
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 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 os
import tempfile
import shutil

# Create a temporary directory structure with the required files
temp_dir = tempfile.mkdtemp()

# Create a subdirectory
subdir_path = os.path.join(temp_dir, "subdir1")
os.makedirs(subdir_path)

# Create the pairs_output_new.txt file with sample data
pairs_file = os.path.join(subdir_path, "pairs_output_new.txt")
with open(pairs_file, 'w') as f:
    f.write("img1.jpg img2.jpg ref_video.jpg ref_video1.jpg ref1.jpg ref2.jpg ref3.jpg ref4.jpg ref5.jpg gt1.jpg gt2.jpg gt3.jpg\n")
    f.write("img3.jpg img4.jpg ref_video2.jpg ref_video3.jpg ref6.jpg ref7.jpg ref8.jpg ref9.jpg ref10.jpg gt4.jpg gt5.jpg gt6.jpg\n")

ARGS = {
    "data_root": 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 list, ndim 2, 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
parse_images Ran
ran on a synthesized input
zhangmozhe/video-colorization/lib/videoloader_imagenet.py
code served (permissive licence) · get_code("0831ed77a7357ffa")
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 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 os
import os.path as osp
import tempfile
import shutil

# Create a temporary directory structure with the required files
temp_dir = tempfile.mkdtemp()

# Create a subdirectory (target folder)
target_folder = osp.join(temp_dir, "target1")
os.makedirs(target_folder, exist_ok=True)

# Create pairs.txt with sample data
pairs_txt_path = osp.join(target_folder, "pairs.txt")
with open(pairs_txt_path, 'w') as f:
    f.write("image1.jpg image2.jpg 1.0\n")
    f.write("image3.jpg image4.jpg 0.8\n")

# Create pairs_mid.txt with sample data
pairs_mid_txt_path = osp.join(target_folder, "pairs_mid.txt")
with open(pairs_mid_txt_path, 'w') as f:
    f.write("image5.jpg image6.jpg 0.5\n")

# Create pairs_bad.txt with sample data
pairs_bad_txt_path = osp.join(target_folder, "pairs_bad.txt")
with open(pairs_bad_txt_path, 'w') as f:
    f.write("image7.jpg image8.jpg 0.1\n")

# Create another target folder without mid and bad files
target_folder2 = osp.join(temp_dir, "target2")
os.makedirs(target_folder2, exist_ok=True)

pairs_txt_path2 = osp.join(target_folder2, "pairs.txt")
with open(pairs_txt_path2, 'w') as f:
    f.write("imageA.jpg imageB.jpg 0.9\n")

ARGS = {
    "dir": temp_dir,
    "with_bad": True,
    "with_mid": True,
}
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 list, ndim 2, 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
pil_loader Ran
ran, honoured the contract we drafted
zhangmozhe/video-colorization/lib/videoloader_imagenet.py
pointer only (licence: MIT); the stored copy get_code serves, from YuemingJin/MTRCNet-CL, is pointer only (licence: NONE) · get_code("1df9a5ffd9b38c34")
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 YuemingJin/MTRCNet-CL, 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.

post_processing Ran
ran; our contract draft was wrong, not the code
zhangmozhe/video-colorization/models/ContextualLoss.py
code served (permissive licence) · get_code("c4bcfa024dc38e50")
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 torchvision
import numpy as np

torch.manual_seed(0)

# The function takes a single parameter: tensor
# Looking at the function body:
# - tensor is passed to postpa (a Compose of transforms)
# - postpa expects a tensor and applies:
#   1. Lambda that multiplies by 1.0/255
#   2. Normalize with specific mean/std
#   3. Lambda that reorders channels [2,1,0]
# - Then clipping is applied (t[t > 1] = 1, t[t < 0] = 0)
# - Then postpb converts to PIL Image (requires 3D tensor with shape (C, H, W) or (H, W))
# - Finally converts to numpy array

# Create a small tensor with shape (3, 4, 5) representing (C, H, W)
# This will work with the channel reordering [2,1,0] and PIL conversion
tensor = torch.randint(0, 256, (3, 4, 5), dtype=torch.float32)

ARGS = {
    "tensor": tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch, torchvision — 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_mytensor Ran
ran on a synthesized input
zhangmozhe/video-colorization/lib/functional.py
code served (permissive licence) · get_code("e7147011e565d852")
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, 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 numpy array to use as input
# Using a 3D array (height=4, width=3, channels=2) to test the transpose operation
pic = np.random.randint(0, 256, size=(4, 3, 2), dtype=np.uint8)

ARGS = {
    "pic": pic
}
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 (2, 4, 3) — shape (2, 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
to_pil_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
zhangmozhe/video-colorization/lib/functional.py
code served (permissive licence) · get_code("0b61f6fc235b392b")
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 Image. 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
from PIL import Image

torch.manual_seed(0)

# Create a valid tensor image (3D tensor with shape C x H x W)
# Using uint8 values in range [0, 255] for RGB
tensor_pic = torch.randint(0, 256, (3, 4, 5), dtype=torch.uint8)

# Alternative: create a numpy image (3D ndarray with shape H x W x C)
numpy_pic = np.random.randint(0, 256, (4, 5, 3), dtype=np.uint8)

ARGS = {
    'pic': tensor_pic,
    'mode': None
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
frame_colorization Not yet run
unverified (harvested, no recorded run)
zhangmozhe/video-colorization/models/FrameColor.py
code served (permissive licence) · get_code("c68601ec117937e3")
How it ran

no invocation recorded.

to_tensor Not yet run
unverified (harvested, no recorded run)
zhangmozhe/video-colorization/lib/functional.py
code served (permissive licence) · get_code("17d5277dba9534b9")
How it ran

no invocation recorded.

warp_color Not yet run
unverified (harvested, no recorded run)
zhangmozhe/video-colorization/models/FrameColor.py
code served (permissive licence) · get_code("2be1b9a4b327908e")
How it ran

no invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 6 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 0 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
pil_loader 28 other papers
4 dated earlier, 24 later
1702.00758 (2017-02)
HashNet: Deep Learning to Hash by Continuation
1805.07932 (2018-05)
Bilinear Attention Networks
1807.06587 (2018-07)
Deep Exemplar-based Colorization
and 25 more not named here
to_pil_image 2 other papers
1 dated earlier, 1 later
1807.06587 (2018-07)
Deep Exemplar-based Colorization
2502.05749 (2025-02)
UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control
to_tensor 2 other papers
1 dated earlier, 1 later
1807.06587 (2018-07)
Deep Exemplar-based Colorization
2502.05749 (2025-02)
UniDB: A Unified Diffusion Bridge Framework via Stochastic Optimal Control
CustomFunc 1 other paper
1 dated earlier
1807.06587 (2018-07)
Deep Exemplar-based Colorization
post_processing 1 other paper
1 later
2004.05571 (2020-04)
Cross-domain Correspondence Learning for Exemplar-based Image Translation
to_mytensor 1 other paper
1 dated earlier
1807.06587 (2018-07)
Deep Exemplar-based Colorization

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

This paper presents the first end-to-end network for exemplar-based video colorization. The main challenge is to achieve temporal consistency while remaining faithful to the reference style. To address this issue, we introduce a recurrent framework that unifies the semantic correspondence and color propagation steps. Both steps allow a provided reference image to guide the colorization of every frame, thus reducing accumulated propagation errors. Video frames are colorized in sequence based on the colorization history, and its coherency is further enforced by the temporal consistency loss. All of these components, learned end-to-end, help produce realistic videos with good temporal stability. Experiments show our result is superior to the state-of-the-art methods both quantitatively and qualitatively.

For agents

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

get_harvested_code_for_paper("1906.09909")
get_code_for_paper("1906.09909")
have("1906.09909")

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

curl https://syntology.ai/api/ran/1906.09909.json

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

[![Syntology run record](https://syntology.ai/api/ran/1906.09909.svg)](https://syntology.ai/paper/1906.09909)

Connect an agent — have() is free.