SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1504.06993 · 2015

Compression Artifacts Reduction by a Deep Convolutional Network

arXiv · PDF · Open in the Atlas

Code that ran

7 of 12 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, 0 violated it and 7 have no contract verdict; 0 failures of our instrument; 5 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/1504.06993.json · badge: /api/ran/1504.06993.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
vinayak19th/ARCNN-keras community (classifier label)
classifier basis not recorded on the link
7 ran · 5 no recorded run
FunctionStatusWhere it lives
create_artifact_dataset Ran
ran on a synthesized input
vinayak19th/ARCNN-keras/dataset.py
code served (permissive licence) · get_code("f96f5b284218bb71")
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 CacheDataset. 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 tensorflow as tf
import tempfile
import os
import numpy as np
from PIL import Image

# Create a temporary directory with small test JPEG files
tmpdir = tempfile.mkdtemp()

# Generate 2 small dummy JPEG images (4x4 RGB)
for i in range(2):
    img_array = np.random.randint(0, 256, (4, 4, 3), dtype=np.uint8)
    img = Image.fromarray(img_array)
    img.save(os.path.join(tmpdir, f'test_{i}.jpg'))

ARGS = {
    'fpath': tmpdir,
    'batch_size': 2,
    'p': 2,
    's': 1,
    'jpq': (10, 20),
    'fformat': 'jpg'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type CacheDataset — a CacheDataset output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a CacheDataset 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
create_patches Ran
ran on a synthesized input
vinayak19th/ARCNN-keras/dataset.py
code served (permissive licence) · get_code("f3b005e16c0f62e9")
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. 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 tensorflow as tf

# Create small test tensors
# The function uses tf.image.extract_patches which expects 4D tensors: (batch, height, width, channels)
# Using small dimensions: batch=2, height=4, width=3, channels=1

batch_size = 2
height = 4
width = 3
channels = 1

# Create random input tensors
x = tf.random.normal((batch_size, height, width, channels))
y = tf.random.normal((batch_size, height, width, channels))

# Patch size and stride
p = 2  # patch size
s = 1  # stride

ARGS = {
    'x': x,
    'y': y,
    'p': p,
    's': s
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — 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
custom_loss Ran
ran on a synthesized input
vinayak19th/ARCNN-keras/fine_tune.py
code served (permissive licence) · get_code("211ee3f7bb5d1a67")
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 SymbolicTensor. 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 tensorflow as tf
import numpy as np

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

# Create small tensor arguments
# y_true: ground truth images, shape (batch, height, width, channels)
y_true = tf.constant(np.random.uniform(0, 1, size=(2, 4, 4, 3)).astype(np.float32))

# y_pred: predicted images, same shape as y_true
y_pred = tf.constant(np.random.uniform(0, 1, size=(2, 4, 4, 3)).astype(np.float32))

ARGS = {
    "y_true": y_true,
    "y_pred": y_pred,
}
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 SymbolicTensor — a SymbolicTensor output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_ARCNN_lite Ran
ran on a synthesized input
vinayak19th/ARCNN-keras/model.py
code served (permissive licence) · get_code("e8b6af4a8b1b8c3a")
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 Functional. 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 tensorflow as tf
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, Conv2D

# The function get_ARCNN_lite takes one optional parameter: input_shape
# It constructs a Keras functional model and returns it
# The function doesn't actually use the returned model, just builds and returns it

ARGS = {
    'input_shape': (32, 32, 1)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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
process_image_SR Ran
ran on a synthesized input
vinayak19th/ARCNN-keras/infer.py
code served (permissive licence) · get_code("1fa1f185b1d28b86")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import PIL
from io import BytesIO

# Create a small test image in memory
img_array = np.random.randint(0, 256, (8, 6, 3), dtype=np.uint8)
img = PIL.Image.fromarray(img_array, mode='RGB')

# Save to BytesIO and get the path-like object
img_bytes = BytesIO()
img.save(img_bytes, format='PNG')
img_bytes.seek(0)

# Create a temporary file path for testing
import tempfile
import os

temp_dir = tempfile.mkdtemp()
impath = os.path.join(temp_dir, 'test_image.png')

# Save the test image to disk
test_img = PIL.Image.new('RGB', (8, 6), color=(100, 150, 200))
test_img.save(impath)

ARGS = {
    'impath': impath
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — 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
psnr Ran
ran on a synthesized input
vinayak19th/ARCNN-keras/fine_tune.py
code served (permissive licence) · get_code("9bf561b55d08adc6")
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 SymbolicTensor. 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 tensorflow as tf
import numpy as np

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

# Create small image tensors normalized to [0, 1] range
# PSNR expects images with values in [0, max_val] range
# Using shape (batch=2, height=4, width=3, channels=3) for RGB images
batch_size = 2
height = 4
width = 3
channels = 3

# Create ground truth images
y_true = tf.constant(
    np.random.uniform(0, 1, size=(batch_size, height, width, channels)).astype(np.float32)
)

# Create predicted images (slightly different from ground truth)
y_pred = tf.constant(
    np.random.uniform(0, 1, size=(batch_size, height, width, channels)).astype(np.float32)
)

ARGS = {
    "y_true": y_true,
    "y_pred": y_pred,
}
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 SymbolicTensor — a SymbolicTensor 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
psnr Ran
ran on a synthesized input
vinayak19th/ARCNN-keras/infer.py
code served (permissive licence) · get_code("33b39f793307ff50")
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 SymbolicTensor. 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 tensorflow as tf
import numpy as np

# Create small image tensors with values in [0, 1] range
# PSNR compares two images, so we need y_true and y_pred
# Using batch_size=2, height=4, width=4, channels=3
batch_size = 2
height = 4
width = 4
channels = 3

# Create random image tensors with values in [0, 1]
np.random.seed(0)
y_true = tf.constant(np.random.rand(batch_size, height, width, channels).astype(np.float32))
y_pred = tf.constant(np.random.rand(batch_size, height, width, channels).astype(np.float32))

ARGS = {
    "y_true": y_true,
    "y_pred": y_pred,
}
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 SymbolicTensor — a SymbolicTensor 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
create_pairs Not yet run
unverified (harvested, no recorded run)
vinayak19th/ARCNN-keras/dataset.py
code served (permissive licence) · get_code("4d1f937d83bdb2ba")
How it ran

no invocation recorded.

get_ARCNN Not yet run
unverified (harvested, no recorded run)
vinayak19th/ARCNN-keras/model.py
code served (permissive licence) · get_code("abd86e47714097fd")
How it ran

no invocation recorded.

get_Fast_ARCNN Not yet run
unverified (harvested, no recorded run)
vinayak19th/ARCNN-keras/model.py
code served (permissive licence) · get_code("20b5da841196b405")
How it ran

no invocation recorded.

ssim Not yet run
unverified (harvested, no recorded run)
vinayak19th/ARCNN-keras/fine_tune.py
code served (permissive licence) · get_code("6672023a8374b970")
How it ran

no invocation recorded.

ssim Not yet run
unverified (harvested, no recorded run)
vinayak19th/ARCNN-keras/infer.py
code served (permissive licence) · get_code("af34d185f9555e29")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 12 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.

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

Lossy compression introduces complex compression artifacts, particularly the blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restores sharpened images that are accompanied with ringing effects. Inspired by the deep convolutional networks (DCN) on super-resolution, we formulate a compact and efficient network for seamless attenuation of different compression artifacts. We also demonstrate that a deeper model can be effectively trained with the features learned in a shallow network. Following a similar "easy to hard" idea, we systematically investigate several practical transfer settings and show the effectiveness of transfer learning in low-level vision problems. Our method shows superior performance than the state-of-the-arts both on the benchmark datasets and the real-world use case (i.e. Twitter). In addition, we show that our method can be applied as pre-processing to facilitate other low-level vision routines when they take compressed images as input.

For agents

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

get_harvested_code_for_paper("1504.06993")
get_code_for_paper("1504.06993")
have("1504.06993")

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

curl https://syntology.ai/api/ran/1504.06993.json

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

[![Syntology run record](https://syntology.ai/api/ran/1504.06993.svg)](https://syntology.ai/paper/1504.06993)

Connect an agent — have() is free.