SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.01311 · 2019

Fully Automatic Video Colorization with Self-Regularization and Diversity

arXiv · PDF · Open in the Atlas

Code that ran

7 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 1 violated it and 6 have no contract verdict; 0 failures of our instrument; 3 no recorded run), measured 2026-11-21; 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/1908.01311.json · badge: /api/ran/1908.01311.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
ChenyangLEI/Fully-Automatic-Video-Colorization-with-Self-Regularization-and-Diversity canonical (classifier label)
classifier basis: census
7 ran · 3 no recorded run
FunctionStatusWhere it lives
Bilateral_NN Ran
ran on a synthesized input
ChenyangLEI/Fully-Automatic-Video-Colorization-with-Self-Regularization-and-Diversity/main_whole.py
code served (permissive licence) · get_code("c11c102bbcfa525a")
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 int, shape (12, 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 numpy as np
from sklearn.neighbors import NearestNeighbors

# Create a small color image (height=4, width=3, channels=3 for RGB)
color_image = np.random.rand(4, 3, 3).astype(np.float32)

# Create and fit the NearestNeighbors object
neigh = NearestNeighbors(n_neighbors=5)

ARGS = {
    "color_image": color_image,
    "neigh": neigh
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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 int, shape (12, 5) — shape (12, 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
check_image Ran
ran on a synthesized input
ChenyangLEI/Fully-Automatic-Video-Colorization-with-Self-Regularization-and-Diversity/utils.py
code served (permissive licence) · get_code("5902e315750725ee")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 3, dtype family float, 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 tensorflow as tf
import numpy as np

# Create a valid 3D image tensor with shape (height, width, 3_channels)
image_3d = tf.constant(np.random.rand(4, 5, 3).astype(np.float32))

ARGS = {
    "image": image_3d
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 3, dtype family float, 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
compute_error Ran
ran on a synthesized input
ChenyangLEI/Fully-Automatic-Video-Colorization-with-Self-Regularization-and-Diversity/loss.py
code served (permissive licence) · get_code("a749989daf2242cf")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 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 tensorflow as tf
import numpy as np

# Create small tensor arguments for the function
# compute_error takes two parameters: real and fake
# Both should be tensors that can be subtracted and have abs() and reduce_mean() applied

real_data = tf.constant([[1.0, 2.0, 3.0, 4.0],
                         [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)

fake_data = tf.constant([[1.1, 2.1, 2.9, 4.2],
                         [4.9, 6.1, 7.1, 7.9]], dtype=tf.float32)

ARGS = {
    "real": real_data,
    "fake": fake_data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 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_image_file Ran
ran, violated the contract we drafted
ChenyangLEI/Fully-Automatic-Video-Colorization-with-Self-Regularization-and-Diversity/utils.py
code served (permissive licence) · get_code("25d498f122b53d79")
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

ARGS = {
    "filename": "test_image.png"
}
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
lrelu Ran
ran on a synthesized input
ChenyangLEI/Fully-Automatic-Video-Colorization-with-Self-Regularization-and-Diversity/network.py
code served (permissive licence) · get_code("f406422099514e4c")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 2, dtype family float, shape (2, 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 tensorflow as tf
import numpy as np

def lrelu(x):
    return tf.maximum(x * 0.2, x)

# Create a small TensorFlow tensor for testing
x_value = tf.constant([[-1.0, 0.5, -0.3, 2.0], [0.1, -0.8, 1.5, -0.2]], dtype=tf.float32)

ARGS = {
    'x': x_value
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 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
read_flow Ran
ran on a synthesized input
ChenyangLEI/Fully-Automatic-Video-Colorization-with-Self-Regularization-and-Diversity/myflowlib.py
code served (permissive licence) · get_code("355a0e7493195d88")
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 (3, 4, 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 numpy as np
import tempfile
import os

# Create a temporary .flo file with valid Middlebury optical flow format
temp_dir = tempfile.mkdtemp()
temp_flo_path = os.path.join(temp_dir, "test_flow.flo")

# Write a valid .flo file
with open(temp_flo_path, 'wb') as f:
    # Magic number for .flo format
    magic = np.array([202021.25], dtype=np.float32)
    magic.tofile(f)
    
    # Width and height
    w = np.array([4], dtype=np.int32)
    h = np.array([3], dtype=np.int32)
    w.tofile(f)
    h.tofile(f)
    
    # Optical flow data: 2 channels (u, v) for each pixel
    flow_data = np.random.randn(2 * 4 * 3).astype(np.float32)
    flow_data.tofile(f)

ARGS = {
    "filename": temp_flo_path
}
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 3, dtype family float, shape (3, 4, 2) — shape (3, 4, 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
smoothL1_loss Ran
ran on a synthesized input
ChenyangLEI/Fully-Automatic-Video-Colorization-with-Self-Regularization-and-Diversity/loss.py
code served (permissive licence) · get_code("e0dcb0458790008e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned EagerTensor, ndim 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 tensorflow as tf
import numpy as np

# Create small TensorFlow tensors for x and y
x = tf.constant([[1.0, 2.0, 3.0, 4.0], [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)
y = tf.constant([[1.1, 2.05, 3.02, 4.1], [5.05, 6.02, 7.1, 8.0]], dtype=tf.float32)

# Define sigma parameter
sigma = 0.05

ARGS = {
    "x": x,
    "y": y,
    "sigma": sigma
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 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
get_names Not yet run
unverified (harvested, no recorded run)
ChenyangLEI/Fully-Automatic-Video-Colorization-with-Self-Regularization-and-Diversity/utils.py
code served (permissive licence) · get_code("e11b2b71eb327267")
How it ran

no invocation recorded.

video2frames Not yet run
unverified (harvested, no recorded run)
ChenyangLEI/Fully-Automatic-Video-Colorization-with-Self-Regularization-and-Diversity/video_utils.py
code served (permissive licence) · get_code("003af94cd199df87")
How it ran

no invocation recorded.

visualize_flow Not yet run
unverified (harvested, no recorded run)
ChenyangLEI/Fully-Automatic-Video-Colorization-with-Self-Regularization-and-Diversity/myflowlib.py
code served (permissive licence) · get_code("a2a77cea60ecb38a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 1 later) and 8 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
is_image_file 62 other papers
9 dated earlier, 53 later
1609.04802 (2016-09)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
1703.07511 (2017-03)
Deep Photo Style Transfer
1710.10916 (2017-10)
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
and 59 more not named here
lrelu 3 other papers
3 dated earlier
1603.04042 (2016-03)
Deep Interactive Object Selection
1701.06487 (2017-01)
Dirty Pixels: Towards End-to-End Image Processing and Perception
1805.01934 (2018-05)
Learning to See in the Dark

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 2026-11-21.

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 fully automatic approach to video colorization with self-regularization and diversity. Our model contains a colorization network for video frame colorization and a refinement network for spatiotemporal color refinement. Without any labeled data, both networks can be trained with self-regularized losses defined in bilateral and temporal space. The bilateral loss enforces color consistency between neighboring pixels in a bilateral space and the temporal loss imposes constraints between corresponding pixels in two nearby frames. While video colorization is a multi-modal problem, our method uses a perceptual loss with diversity to differentiate various modes in the solution space. Perceptual experiments demonstrate that our approach outperforms state-of-the-art approaches on fully automatic video colorization. The results are shown in the supplementary video at https://youtu.be/Y15uv2jnK-4

For agents

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

get_harvested_code_for_paper("1908.01311")
get_code_for_paper("1908.01311")
have("1908.01311")

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

curl https://syntology.ai/api/ran/1908.01311.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.01311.svg)](https://syntology.ai/paper/1908.01311)

Connect an agent — have() is free.