SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2207.13374 · ECCV · 2022

Efficient Video Deblurring Guided by Motion Magnitude

Lin Wang, Yinqiang Zheng, Yunfan Lu, Ye Gao, Yusheng Wang, Zhihang Zhong, Atsushi Yamashita

arXiv · PDF · Open in the Atlas

Code that ran

15 of 18 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (11 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 11 have no contract verdict; 4 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/2207.13374.json · badge: /api/ran/2207.13374.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
sollynoay/MMP-RNN community
Papers with Code archive
14 ran · 3 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
CALayer Ran
ran on a synthesized input · constructed an object; no result was computed
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("97e8836b4b2a9a4c")
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 an instance of its own class, CALayer: the run constructed the object and did not call it, so no result was computed. 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 = {
    'channel': 16,
    'reduction': 4
}
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 CALayer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CALayer 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
CAT Ran
ran on a synthesized input · constructed an object; no result was computed
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("cd76941e48236e79")
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 an instance of its own class, CAT: the run constructed the object and did not call it, so no result was computed. 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)

class Para:
    def __init__(self, future_frames, past_frames, n_features):
        self.future_frames = future_frames
        self.past_frames = past_frames
        self.n_features = n_features

# Create a small parameter object
# frames = future_frames + past_frames + 1 = 2 + 1 + 1 = 4
# n_feats = 2
# fusion input channels: frames * (5 * n_feats) = 4 * (5 * 2) = 40
para = Para(future_frames=2, past_frames=1, n_features=2)

# Create input tensors for forward pass
# hs should be a list of tensors that will be concatenated along dim=1
# Each tensor should have shape (batch, channels, height, width)
# After concat along dim=1, we need shape (batch, 4*5*2, height, width) = (batch, 40, height, width)
# So each of 4 tensors should have (batch, 10, height, width)
batch_size = 2
height = 3
width = 4
channels_per_frame = 5 * para.n_features  # 10

hs = [
    torch.randn(batch_size, channels_per_frame, height, width),
    torch.randn(batch_size, channels_per_frame, height, width),
    torch.randn(batch_size, channels_per_frame, height, width),
    torch.randn(batch_size, channels_per_frame, height, width),
]

ARGS = {
    "para": para,
}
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 CAT — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a CAT 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
Down Ran
ran on a synthesized input · constructed an object; no result was computed
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("34425d3da3c2002f")
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 an instance of its own class, Down: the run constructed the object and did not call it, so no result was computed. 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)

# The Down class takes in_channels and out_channels as parameters
# It creates a Sequential with MaxPool2d and DoubleConv
# We need to provide valid integer values for these

ARGS = {
    'in_channels': 3,
    'out_channels': 4
}
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 Down — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Down 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
MMAMLayer Ran
ran on a synthesized input · constructed an object; no result was computed
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("94e9be4afb4bc7cc")
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 an instance of its own class, MMAMLayer: the run constructed the object and did not call it, so no result was computed. 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)

# Create a minimal config object that has the n_features attribute
class ParaConfig:
    def __init__(self, n_features):
        self.n_features = n_features

# Create the parameter object
para = ParaConfig(n_features=8)

# Create sample tensors for x and y
# x should have shape (batch, channels, height, width)
# y should have shape (batch, 1, height, width) since MMAM_conv0 expects 1 input channel
x = torch.randn(2, 8, 4, 3)  # batch=2, channels=8, height=4, width=3
y = torch.randn(2, 1, 4, 3)  # batch=2, channels=1, height=4, width=3

ARGS = {
    'para': para,
}
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 MMAMLayer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a MMAMLayer 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
RDB Ran
ran on a synthesized input · constructed an object; no result was computed
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("0db765fc2faaba7e")
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 an instance of its own class, RDB: the run constructed the object and did not call it, so no result was computed. 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': 4,
    'growthRate': 3,
    'num_layer': 2,
    'activation': 'gelu',
    'do_attention_ca': False,
    'do_attention_sa': False,
}
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 RDB — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a RDB 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
RDB_DS Ran
ran on a synthesized input · constructed an object; no result was computed
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("f4139fcc9fbb1f5e")
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 an instance of its own class, RDB_DS: the run constructed the object and did not call it, so no result was computed. 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': 3,
    'growthRate': 32,
    'out_channels': 64,
    'num_layer': 2,
    'activation': 'gelu'
}
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 RDB_DS — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a RDB_DS 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
RDNet Ran
ran on a synthesized input · constructed an object; no result was computed
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("8a7d9cc56b106e06")
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 an instance of its own class, RDNet: the run constructed the object and did not call it, so no result was computed. 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': 4,
    'growthRate': 3,
    'num_layer': 2,
    'num_blocks': 2,
    'activation': 'gelu',
    'do_attention_ca': False,
    'do_attention_sa': False,
}
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 RDNet — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a RDNet 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
Reconstructor Ran
ran on a synthesized input · constructed an object; no result was computed
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("5803e5cec982ffc6")
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 an instance of its own class, Reconstructor: the run constructed the object and did not call it, so no result was computed. 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)

class MockPara:
    def __init__(self):
        self.future_frames = 2
        self.past_frames = 2
        self.n_features = 4
        self.n_blocks_b = 2

para = MockPara()

ARGS = {
    "para": para
}
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 Reconstructor — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Reconstructor 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
SALayer Ran
ran on a synthesized input · constructed an object; no result was computed
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("754e463721d28afa")
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 an instance of its own class, SALayer: the run constructed the object and did not call it, so no result was computed. 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)

# SALayer.__init__ takes kernel_size parameter
# SALayer.forward takes x and bm tensors
# x should be shape (batch, channels, height, width)
# bm should be compatible for concatenation with mean/max of x along dim=1

# Create sample tensors for forward pass
batch_size = 2
channels = 4
height = 3
width = 3

# x tensor: (batch, channels, height, width)
x = torch.randn(batch_size, channels, height, width)

# For forward: avg_out and max_out will be (batch, 1, height, width)
# They get concatenated on dim=1, so result is (batch, 2, height, width)
# bm must be (batch, 1, height, width) to concatenate with them
bm = torch.randn(batch_size, 1, height, width)

ARGS = {
    "kernel_size": 7,
}
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 SALayer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a SALayer 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
Up Ran
ran on a synthesized input · constructed an object; no result was computed
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("54886eb0c15a8e3a")
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 an instance of its own class, Up: the run constructed the object and did not call it, so no result was computed. 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': 8,
    'out_channels': 4,
    'bilinear': True
}
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 Up — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a Up 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
actFunc Ran
ran; our contract draft was wrong, not the code
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("bb558c38a457b8d9")
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 ReLU. 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)

# The function takes 'act' as the first positional argument (a string)
# and *args, **kwargs which are not used in the function body
# The function only calls .lower() on 'act' and compares it to various strings

ARGS = {
    'act': 'relu',
}
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 ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU 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
conv1x1 Ran
ran; our contract draft was wrong, not the code
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("9bed061f167dd318")
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 Conv2d. 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": 3,
    "out_channels": 64,
    "stride": 1,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
this paper's copy was not recorded; identical code first harvested from BruceBinBoxing/ST-ResNet-Pytorch
pointer only; the stored copy get_code serves, from BruceBinBoxing/ST-ResNet-Pytorch, is pointer only (licence: NONE) · get_code("f3d374db4177f20c")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

conv5x5 Ran
ran; our contract draft was wrong, not the code
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("05b9fb4be8292106")
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 Conv2d. 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": 3,
    "out_channels": 16,
    "stride": 1,
}
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 Conv2d — a Conv2d output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Conv2d 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
dense_layer Ran
ran on a synthesized input · constructed an object; no result was computed
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("00f948a021c281d9")
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 an instance of its own class, dense_layer: the run constructed the object and did not call it, so no result was computed. 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': 3,
    'growthRate': 4,
    'activation': 'gelu'
}
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 dense_layer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a dense_layer 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
Model Not yet run
unverified (harvested, no recorded run)
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("13a7894f8bb62fb4")
How it ran

no invocation recorded.

RDBCell Not yet run
unverified (harvested, no recorded run)
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("b6e21fb0d71a719a")
How it ran

no invocation recorded.

UNet Not yet run
unverified (harvested, no recorded run)
sollynoay/MMP-RNN/MMP-RNN/model/MMPRNN.py
code served (permissive licence) · get_code("801b9430794df229")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 3 the same month, 4 later) and 13 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
conv1x1
brick of this paper's assembly: helper
12 other papers
4 dated earlier, 1 the same month, 7 later · 1 only as an assembly brick
2006.04139 (2020-06)
Learning Texture Transformer Network for Image Super-Resolution
2106.16028 (2021-06)
Real-world Video Deblurring: A Benchmark Dataset and An Efficient Recurrent Neural Network
2112.05150 (2021-12)
Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring
and 9 more not named here
conv3x3
brick of this paper's assembly: helper
10 other papers
4 dated earlier, 1 the same month, 5 later · 1 only as an assembly brick
1610.00081 (2016-10)
Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction
2006.04139 (2020-06)
Learning Texture Transformer Network for Image Super-Resolution
2106.16028 (2021-06)
Real-world Video Deblurring: A Benchmark Dataset and An Efficient Recurrent Neural Network
and 7 more not named here
Down
brick of this paper's assembly: helper
5 other papers
2 dated earlier, 3 later · 2 only as an assembly brick
1505.04597 (2015-05)
U-Net: Convolutional Networks for Biomedical Image Segmentation
2011.05479 (2020-11)
ForestNet: Classifying Drivers of Deforestation in Indonesia using Deep Learning on Satellite Imagery
2309.04814 (2023-09)
Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video
and 2 more not named here
conv5x5
brick of this paper's assembly: helper
3 other papers
2 dated earlier, 1 later
2106.16028 (2021-06)
Real-world Video Deblurring: A Benchmark Dataset and An Efficient Recurrent Neural Network
2112.05150 (2021-12)
Deep Recurrent Neural Network with Multi-scale Bi-directional Propagation for Video Deblurring
2407.09059 (2024-07)
Domain-adaptive Video Deblurring via Test-time Blurring
actFunc
brick of this paper's assembly: helper
1 other paper
1 the same month · 1 only as an assembly brick
2207.10123 (2022-07)
Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance

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

Video deblurring is a highly under-constrained problem due to the spatially and temporally varying blur. An intuitive approach for video deblurring includes two steps: a) detecting the blurry region in the current frame; b) utilizing the information from clear regions in adjacent frames for current frame deblurring. To realize this process, our idea is to detect the pixel-wise blur level of each frame and combine it with video deblurring. To this end, we propose a novel framework that utilizes the motion magnitude prior (MMP) as guidance for efficient deep video deblurring. Specifically, as the pixel movement along its trajectory during the exposure time is positively correlated to the level of motion blur, we first use the average magnitude of optical flow from the high-frequency sharp frames to generate the synthetic blurry frames and their corresponding pixel-wise motion magnitude maps. We then build a dataset including the blurry frame and MMP pairs. The MMP is then learned by a compact CNN by regression. The MMP consists of both spatial and temporal blur level information, which can be further integrated into an efficient recurrent neural network (RNN) for video deblurring. We conduct intensive experiments to validate the effectiveness of the proposed methods on the public datasets. Our codes are available at https://github.com/sollynoay/MMP-RNN.

For agents

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

get_harvested_code_for_paper("2207.13374")
get_code_for_paper("2207.13374")
have("2207.13374")

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

curl https://syntology.ai/api/ran/2207.13374.json

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

[![Syntology run record](https://syntology.ai/api/ran/2207.13374.svg)](https://syntology.ai/paper/2207.13374)

Connect an agent — have() is free.