SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2109.14573 · ICCV · 2021

Towards Flexible Blind JPEG Artifacts Removal

Radu Timofte, Kai Zhang, Jiaxi Jiang

arXiv · PDF · Open in the Atlas

Code that ran

9 of 11 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 2 have no contract verdict; 7 failures of our instrument; 2 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/2109.14573.json · badge: /api/ran/2109.14573.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
jiaxi-jiang/fbcnn marked official in Papers with Code
Papers with Code archive
9 ran · 2 no recorded run
FunctionStatusWhere it lives
QFAttention Ran
ran on a synthesized input
jiaxi-jiang/fbcnn/models/network_fbcnn.py
code served (permissive licence) · get_code("504364eda535d2ec")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from collections import OrderedDict

def conv(in_channels=64, out_channels=64, kernel_size=3, stride=1, padding=1, bias=True, mode='CBR', negative_slope=0.2):
    L = []
    for t in mode:
        if t == 'C':
            L.append(nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, padding=padding, bias=bias))
        elif t == 'T':
            L.append(nn.ConvTranspose2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, padding=padding, bias=bias))
        elif t == 'B':
            L.append(nn.BatchNorm2d(out_channels, momentum=0.9, eps=0.0001, affine=True))
        elif t == 'I':
            L.append(nn.InstanceNorm2d(out_channels, affine=True))
        elif t == 'R':
            L.append(nn.ReLU(inplace=True))
        elif t == 'r':
            L.append(nn.ReLU(inplace=False))
        elif t == 'L':
            L.append(nn.LeakyReLU(negative_slope=negative_slope, inplace=True))
        elif t == 'l':
            L.append(nn.LeakyReLU(negative_slope=negative_slope, inplace=False))
        elif t == '2':
            L.append(nn.PixelShuffle(upscale_factor=2))
        elif t == '3':
            L.append(nn.PixelShuffle(upscale_factor=3))
        elif t == '4':
            L.append(nn.PixelShuffle(upscale_factor=4))
        elif t == 'U':
            L.append(nn.Upsample(scale_factor=2, mode='nearest'))
        elif t == 'u':
            L.append(nn.Upsample(scale_factor=3, mode='nearest'))
        elif t == 'v':
            L.append(nn.Upsample(scale_factor=4, mode='nearest'))
        elif t == 'M':
            L.append(nn.MaxPool2d(kernel_size=kernel_size, stride=stride, padding=0))
        elif t == 'A':
            L.append(nn.AvgPool2d(kernel_size=kernel_size, stride=stride, padding=0))
        else:
            raise NotImplementedError('Undefined type: '.format(t))
    return sequential(*L)

def sequential(*args):
    """Advanced nn.Sequential.

    Args:
        nn.Sequential, nn.Module

    Returns:
        nn.Sequential
    """
    if len(args) == 1:
        if isinstance(args[0], OrderedDict):
            raise NotImplementedError('sequential does not support OrderedDict input.')
        return args[0]
    modules = []
    for module in args:
        if isinstance(module, nn.Sequential):
            for submodule in module.children():
                modules.append(submodule)
        elif isinstance(module, nn.Module):
            modules.append(module)
    return nn.Sequential(*modules)

class QFAttention(nn.Module):

    def __init__(self, in_channels=64, out_channels=64, kernel_size=3, stride=1, padding=1, bias=True, mode='CRC', negative_slope=0.2):
        super(QFAttention, self).__init__()
        assert in_channels == out_channels, 'Only support in_channels==out_channels.'
        if mode[0] in ['R', 'L']:
            mode = mode[0].lower() + mode[1:]
        self.res = conv(in_channels, out_channels, kernel_size, stride, padding, bias, mode, negative_slope)

    def forward(self, x, gamma, beta):
        gamma = gamma.unsqueeze(-1).unsqueeze(-1)
        beta = beta.unsqueeze(-1).unsqueeze(-1)
        res = gamma * self.res(x) + beta
        return x + res


INIT_ARGS = {
    'in_channels': 4,
    'out_channels': 4,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'bias': True,
    'mode': 'CRC',
    'negative_slope': 0.2
}

ARGS = {
    'x': torch.randn(2, 4, 8, 8),
    'gamma': torch.randn(2, 4),
    'beta': torch.randn(2, 4)
}

if __name__ == '__main__':
    model = QFAttention(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Expected shape: {ARGS['x'].shape}")
    assert output.shape == ARGS['x'].shape, "Output shape mismatch"
    print("Test passed!")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
ResBlock Ran
ran on a synthesized input
jiaxi-jiang/fbcnn/models/network_fbcnn.py
code served (permissive licence) · get_code("2cfea441b848a2ad")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 4, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
from collections import OrderedDict

# Copy the helper functions and ResBlock class
def conv(in_channels=64, out_channels=64, kernel_size=3, stride=1, padding=1, bias=True, mode='CBR', negative_slope=0.2):
    L = []
    for t in mode:
        if t == 'C':
            L.append(nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, padding=padding, bias=bias))
        elif t == 'T':
            L.append(nn.ConvTranspose2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride, padding=padding, bias=bias))
        elif t == 'B':
            L.append(nn.BatchNorm2d(out_channels, momentum=0.9, eps=0.0001, affine=True))
        elif t == 'I':
            L.append(nn.InstanceNorm2d(out_channels, affine=True))
        elif t == 'R':
            L.append(nn.ReLU(inplace=True))
        elif t == 'r':
            L.append(nn.ReLU(inplace=False))
        elif t == 'L':
            L.append(nn.LeakyReLU(negative_slope=negative_slope, inplace=True))
        elif t == 'l':
            L.append(nn.LeakyReLU(negative_slope=negative_slope, inplace=False))
        elif t == '2':
            L.append(nn.PixelShuffle(upscale_factor=2))
        elif t == '3':
            L.append(nn.PixelShuffle(upscale_factor=3))
        elif t == '4':
            L.append(nn.PixelShuffle(upscale_factor=4))
        elif t == 'U':
            L.append(nn.Upsample(scale_factor=2, mode='nearest'))
        elif t == 'u':
            L.append(nn.Upsample(scale_factor=3, mode='nearest'))
        elif t == 'v':
            L.append(nn.Upsample(scale_factor=4, mode='nearest'))
        elif t == 'M':
            L.append(nn.MaxPool2d(kernel_size=kernel_size, stride=stride, padding=0))
        elif t == 'A':
            L.append(nn.AvgPool2d(kernel_size=kernel_size, stride=stride, padding=0))
        else:
            raise NotImplementedError('Undefined type: '.format(t))
    return sequential(*L)

def sequential(*args):
    """Advanced nn.Sequential.

    Args:
        nn.Sequential, nn.Module

    Returns:
        nn.Sequential
    """
    if len(args) == 1:
        if isinstance(args[0], OrderedDict):
            raise NotImplementedError('sequential does not support OrderedDict input.')
        return args[0]
    modules = []
    for module in args:
        if isinstance(module, nn.Sequential):
            for submodule in module.children():
                modules.append(submodule)
        elif isinstance(module, nn.Module):
            modules.append(module)
    return nn.Sequential(*modules)

class ResBlock(nn.Module):

    def __init__(self, in_channels=64, out_channels=64, kernel_size=3, stride=1, padding=1, bias=True, mode='CRC', negative_slope=0.2):
        super(ResBlock, self).__init__()
        assert in_channels == out_channels, 'Only support in_channels==out_channels.'
        if mode[0] in ['R', 'L']:
            mode = mode[0].lower() + mode[1:]
        self.res = conv(in_channels, out_channels, kernel_size, stride, padding, bias, mode, negative_slope)

    def forward(self, x):
        res = self.res(x)
        return x + res


INIT_ARGS = {
    'in_channels': 4,
    'out_channels': 4,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'bias': True,
    'mode': 'CRC',
    'negative_slope': 0.2,
}

ARGS = {
    'x': torch.randn(2, 4, 8, 8),
}

if __name__ == '__main__':
    model = ResBlock(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Expected shape: {ARGS['x'].shape}")
    assert output.shape == ARGS['x'].shape, "Output shape mismatch"
    print("ResBlock test passed!")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
conv Ran
ran; our contract draft was wrong, not the code
jiaxi-jiang/fbcnn/models/network_fbcnn.py
code served (permissive licence) · get_code("0bb3503f833a6f8e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Sequential. 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
from collections import OrderedDict

torch.manual_seed(0)

ARGS = {
    'in_channels': 3,
    'out_channels': 64,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'bias': True,
    'mode': 'CBR',
    'negative_slope': 0.2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
downsample_avgpool Ran
ran; our contract draft was wrong, not the code
jiaxi-jiang/fbcnn/models/network_fbcnn.py
code served (permissive licence) · get_code("bf45710301b68ac5")
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 Sequential. 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)

ARGS = {
    'in_channels': 64,
    'out_channels': 128,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'bias': True,
    'mode': '2R',
    'negative_slope': 0.2,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
downsample_maxpool Ran
ran; our contract draft was wrong, not the code
jiaxi-jiang/fbcnn/models/network_fbcnn.py
code served (permissive licence) · get_code("b6aa67b647a44a13")
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 Sequential. 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)

ARGS = {
    'in_channels': 64,
    'out_channels': 128,
    'kernel_size': 3,
    'stride': 1,
    'padding': 0,
    'bias': True,
    'mode': '2R',
    'negative_slope': 0.2,
}
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 Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
downsample_strideconv Ran
ran; our contract draft was wrong, not the code
jiaxi-jiang/fbcnn/models/network_fbcnn.py
code served (permissive licence) · get_code("229a83919d75f9b5")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Sequential. 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
from collections import OrderedDict

torch.manual_seed(0)

ARGS = {
    'in_channels': 64,
    'out_channels': 128,
    'kernel_size': 2,
    'stride': 2,
    'padding': 0,
    'bias': True,
    'mode': '2R',
    'negative_slope': 0.2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
upsample_convtranspose Ran
ran; our contract draft was wrong, not the code
jiaxi-jiang/fbcnn/models/network_fbcnn.py
code served (permissive licence) · get_code("f71abbb00f56cc8a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Sequential. 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
from collections import OrderedDict

torch.manual_seed(0)

ARGS = {
    'in_channels': 64,
    'out_channels': 3,
    'kernel_size': 2,
    'stride': 2,
    'padding': 0,
    'bias': True,
    'mode': '2R',
    'negative_slope': 0.2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
upsample_pixelshuffle Ran
ran; our contract draft was wrong, not the code
jiaxi-jiang/fbcnn/models/network_fbcnn.py
code served (permissive licence) · get_code("60cf0c34b7b63cb0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Sequential. 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)

ARGS = {
    'in_channels': 64,
    'out_channels': 3,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'bias': True,
    'mode': '2R',
    'negative_slope': 0.2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
upsample_upconv Ran
ran; our contract draft was wrong, not the code
jiaxi-jiang/fbcnn/models/network_fbcnn.py
code served (permissive licence) · get_code("6281229c06037ca0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Sequential. 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)

ARGS = {
    'in_channels': 64,
    'out_channels': 3,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'bias': True,
    'mode': '2R',
    'negative_slope': 0.2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Sequential — a Sequential output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Sequential output the recorded ndim 1 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
FBCNN Not yet run
unverified (harvested, no recorded run)
jiaxi-jiang/fbcnn/models/network_fbcnn.py
code served (permissive licence) · get_code("9e6c6a1d38878851")
How it ran

no invocation recorded.

sequential Not yet run
unverified (harvested, no recorded run)
jiaxi-jiang/fbcnn/models/network_fbcnn.py
code served (permissive licence) · get_code("17f1c0ea54159076")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 7 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 7 later) and 4 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
upsample_pixelshuffle
brick of this paper's assembly: helper
10 other papers
1 dated earlier, 9 later
2008.13751 (2020-08)
Plug-and-Play Image Restoration with Deep Denoiser Prior
2110.03220 (2021-10)
Gradient Step Denoiser for convergent Plug-and-Play
2205.05675 (2022-05)
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
and 7 more not named here
conv
brick of this paper's assembly: helper
9 other papers
1 dated earlier, 8 later
2008.13751 (2020-08)
Plug-and-Play Image Restoration with Deep Denoiser Prior
2203.05568 (2022-03)
Unfolded Deep Kernel Estimation for Blind Image Super-resolution
2205.05675 (2022-05)
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
and 6 more not named here
sequential
brick of this paper's assembly: helper
6 other papers
2 dated earlier, 4 later · 3 only as an assembly brick
2104.03078 (2021-04)
Universal and Flexible Optical Aberration Correction Using Deep-Prior Based Deconvolution
2108.05302 (2021-08)
Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution
2110.00984 (2021-10)
Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement
and 3 more not named here
ResBlock
brick of this paper's assembly: model
2 other papers
2 later
2203.05568 (2022-03)
Unfolded Deep Kernel Estimation for Blind Image Super-resolution
2607.11025 (2026-07)
Reference-Based Face Super-Resolution Using the Spatial Transformer
upsample_upconv
brick of this paper's assembly: helper
2 other papers
2 later
2407.21422 (2024-07)
Revisiting Tampered Scene Text Detection in the Era of Generative AI
2502.09873 (2025-02)
Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal
downsample_strideconv
brick of this paper's assembly: helper
1 other paper
1 later
2203.05568 (2022-03)
Unfolded Deep Kernel Estimation for Blind Image Super-resolution
upsample_convtranspose
brick of this paper's assembly: helper
1 other paper
1 later
2203.05568 (2022-03)
Unfolded Deep Kernel Estimation for Blind Image Super-resolution

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

Training a single deep blind model to handle different quality factors for JPEG image artifacts removal has been attracting considerable attention due to its convenience for practical usage. However, existing deep blind methods usually directly reconstruct the image without predicting the quality factor, thus lacking the flexibility to control the output as the non-blind methods. To remedy this problem, in this paper, we propose a flexible blind convolutional neural network, namely FBCNN, that can predict the adjustable quality factor to control the trade-off between artifacts removal and details preservation. Specifically, FBCNN decouples the quality factor from the JPEG image via a decoupler module and then embeds the predicted quality factor into the subsequent reconstructor module through a quality factor attention block for flexible control. Besides, We find existing methods are prone to fail on non-aligned double JPEG images even with only one pixel shift, and we thus propose a double JPEG degradation model to augment the training data. Extensive experiments on single JPEG images, more general double JPEG images and real-world JPEG images demonstrate that our proposed FBCNN achieves favorable performance against state-of-the-art methods in terms of both quantitative metrics and visual quality.

For agents

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

get_harvested_code_for_paper("2109.14573")
get_code_for_paper("2109.14573")
have("2109.14573")

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

curl https://syntology.ai/api/ran/2109.14573.json

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

[![Syntology run record](https://syntology.ai/api/ran/2109.14573.svg)](https://syntology.ai/paper/2109.14573)

Connect an agent — have() is free.