SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2212.05342 · 2022

Benchmark Dataset and Effective Inter-Frame Alignment for Real-World Video Super-Resolution

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 (0 of them constructed an object rather than computing a result; 4 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 6 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/2212.05342.json · badge: /api/ran/2212.05342.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
hitrainer/eavsr canonical (classifier label)
classifier basis not recorded on the link
15 ran · 3 no recorded run
FunctionStatusWhere it lives
backwarp Ran
ran on a synthesized input
hitrainer/eavsr/models/spy_net.py
code served (permissive licence) · get_code("aed5bf923e379575")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 3, 4, 5) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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

torch.manual_seed(0)

# The function expects:
# - tenInput: a tensor with shape (batch, channels, height, width)
# - tenFlow: a tensor with shape (batch, 2, height, width) representing optical flow

# Create small tensors with distinct dimensions for probing
batch_size = 2
channels = 3
height = 4
width = 5

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

# tenFlow: (batch, 2, height, width) - 2 channels for horizontal and vertical flow
tenFlow = torch.randn(batch_size, 2, height, width)

ARGS = {
    'tenInput': tenInput,
    'tenFlow': tenFlow
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 3, 4, 5) — shape (2, 3, 4, 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
calc_psnr_np Ran
ran on a synthesized input
hitrainer/eavsr/psnr_total.py
code served (permissive licence) · get_code("045675487398c9b5")
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 float, 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 numpy as np
import math

# Create small numpy arrays for sr (super-resolution) and hr (high-resolution)
# Using distinct dimensions to make shapes unambiguous
sr = np.random.randint(0, 256, size=(2, 4, 3, 3), dtype=np.uint8)
hr = np.random.randint(0, 256, size=(2, 4, 3, 3), dtype=np.uint8)

ARGS = {
    "sr": sr,
    "hr": hr,
    "range": 255.0
}
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 float, 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
conv Ran
ran on a synthesized input
hitrainer/eavsr/models/networks.py
code served (permissive licence) · get_code("0eb51f2df17bf1fb")
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': 3,
    'out_channels': 64,
    'kernel_size': 3,
    'stride': 1,
    'padding': 1,
    'output_padding': 0,
    'dilation': 1,
    'groups': 1,
    'bias': True,
    'padding_mode': 'zeros',
    'mode': 'CBR'
}
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
create_window Ran
ran, honoured the contract we drafted
hitrainer/eavsr/models/.ipynb_checkpoints/losses-checkpoint.py
code served (permissive licence) · get_code("6154e3744ece5728")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (3, 1, 5, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from torch.autograd import Variable
from math import exp

torch.manual_seed(0)

def gaussian(window_size, sigma):
    gauss = torch.Tensor([exp(-(x - window_size // 2) ** 2 / float(2 * sigma ** 2)) for x in range(window_size)])
    return gauss / gauss.sum()

def create_window(window_size, channel):
    _1D_window = gaussian(window_size, 1.5).unsqueeze(1)
    _2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0)
    window = Variable(_2D_window.expand(channel, 1, window_size, window_size).contiguous())
    return window

ARGS = {
    "window_size": 5,
    "channel": 3
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (3, 1, 5, 5) — shape (3, 1, 5, 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
create_window Ran
ran, honoured the contract we drafted
hitrainer/eavsr/models/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from cszhilu1998/BracketIRE, is pointer only (licence: NOASSERTION) · get_code("a0dde615fc1dc309")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from cszhilu1998/BracketIRE, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

diff_x Ran
ran; our contract draft was wrong, not the code
hitrainer/eavsr/models/eavsrp_model.py
code served (permissive licence) · get_code("e365505adb10850a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 10, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function diff_x expects:
# - input: a 4D tensor (batch, channels, height, width)
# - r: an integer representing the radius parameter

# Construct a small 4D tensor
# Shape: (batch=2, channels=4, height=10, width=3)
# We need height >= 2*r + 1 for the slicing to work properly
# With r=2, we need height >= 5, so height=10 is sufficient
input_tensor = torch.randn(2, 4, 10, 3)

# The radius parameter
r = 2

ARGS = {
    'input': input_tensor,
    'r': r
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 4, 10, 3) — shape (2, 4, 10, 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
diff_y Ran
ran; our contract draft was wrong, not the code
hitrainer/eavsr/models/eavsrp_model.py
code served (permissive licence) · get_code("e083b81277e9fa37")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 3, 4, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function expects:
# - input: a 4D tensor (batch, channels, height, width)
# - r: an integer parameter that controls the slicing behavior

# Create a small 4D tensor with distinct dimensions for probing
# Shape: (batch=2, channels=3, height=4, width=5)
input_tensor = torch.randn(2, 3, 4, 5)

# r must be chosen such that the slicing operations are valid
# Looking at the function:
# - left = input[:, :, :, r:2*r+1] requires width > 2*r+1
# - middle slicing requires proper bounds
# - right slicing requires proper bounds
# With width=5, we can use r=1:
# - left: [:, :, :, 1:3] (width 1:3)
# - middle: [:, :, :, 3:] - [:, :, :, :-3] (valid)
# - right: [:, :, :, -1:] - [:, :, :, -3:-1] (valid)

r = 1

ARGS = {
    "input": input_tensor,
    "r": r
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 3, 4, 5) — shape (2, 3, 4, 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
estimate Ran
ran on a synthesized input
hitrainer/eavsr/models/spy_net.py
code served (permissive licence) · get_code("90386834977a62ea")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 2, 64, 96) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn
import math

torch.manual_seed(0)

class SimpleFlowNet(nn.Module):
    def __init__(self):
        super(SimpleFlowNet, self).__init__()
        self.conv1 = nn.Conv2d(6, 16, kernel_size=3, padding=1)
        self.conv2 = nn.Conv2d(16, 2, kernel_size=3, padding=1)
    
    def forward(self, tenOne, tenTwo):
        # Concatenate the two input tensors along channel dimension
        concatenated = torch.cat([tenOne, tenTwo], dim=1)
        x = torch.relu(self.conv1(concatenated))
        flow = self.conv2(x)
        return flow

# Create input tensors with shape (batch=2, channels=3, height=64, width=96)
tenOne = torch.randn(2, 3, 64, 96)
tenTwo = torch.randn(2, 3, 64, 96)

# Create the network
net = SimpleFlowNet()

ARGS = {
    'tenOne': tenOne,
    'tenTwo': tenTwo,
    'net': net
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 2, 64, 96) — shape (2, 2, 64, 96) 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
flow_warp Ran
ran; our contract draft was wrong, not the code
hitrainer/eavsr/models/eavsrp_model.py
code served (permissive licence) · get_code("098ea38f98f206b2")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 4, 3, 5) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F

torch.manual_seed(0)

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

# Create a flow tensor: (batch=2, height=3, width=5, 2)
# The last dimension contains (dx, dy) offsets
flow = torch.randn(2, 3, 5, 2) * 0.5

ARGS = {
    'x': x,
    'flow': flow,
    'interpolation': 'bilinear',
    'padding_mode': 'zeros',
    'align_corners': 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 Tensor, ndim 4, dtype family float, shape (2, 4, 3, 5) — shape (2, 4, 3, 5) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
gaussian Ran
ran, honoured the contract we drafted
hitrainer/eavsr/models/.ipynb_checkpoints/losses-checkpoint.py
code served (permissive licence) · get_code("c56b7ef16f309a45")
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 Tensor, ndim 1, dtype family float, shape (5,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
from math import exp

torch.manual_seed(0)

ARGS = {
    "window_size": 5,
    "sigma": 1.0,
}
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 Tensor, ndim 1, dtype family float, shape (5,) — shape (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
gaussian Ran
ran, honoured the contract we drafted
hitrainer/eavsr/models/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from cszhilu1998/BracketIRE, is pointer only (licence: NOASSERTION) · get_code("8ae718c731ac70b0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from cszhilu1998/BracketIRE, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

get_scheduler Ran
ran on a synthesized input
hitrainer/eavsr/models/networks.py
code served (permissive licence) · get_code("82bd3e5c005f2a4f")
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 LambdaLR. 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 torch.optim import Adam

torch.manual_seed(0)

# Create a minimal model
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

# Create model and optimizer
model = SimpleModel()
optimizer = Adam(model.parameters(), lr=0.001)

# Create a minimal options object with required attributes
class OptConfig:
    def __init__(self, lr_policy='linear', niter=100, niter_decay=50, lr_decay_iters=10):
        self.lr_policy = lr_policy
        self.niter = niter
        self.niter_decay = niter_decay
        self.lr_decay_iters = lr_decay_iters

opt = OptConfig(lr_policy='linear', niter=100, niter_decay=50, lr_decay_iters=10)

ARGS = {
    'optimizer': optimizer,
    'opt': opt
}
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 LambdaLR — a LambdaLR output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LambdaLR 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
init_net Ran
ran; our contract draft was wrong, not the code
hitrainer/eavsr/models/networks.py
code served (permissive licence) · get_code("1b0f2564281c40e3")
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 SimpleNet. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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 torch.nn import init

torch.manual_seed(0)

# Create a simple neural network with Conv2d, Linear, and BatchNorm2d layers
class SimpleNet(nn.Module):
    def __init__(self):
        super(SimpleNet, self).__init__()
        self.conv1 = nn.Conv2d(3, 16, kernel_size=3)
        self.bn1 = nn.BatchNorm2d(16)
        self.linear1 = nn.Linear(16, 8)
        self.linear2 = nn.Linear(8, 2)
    
    def forward(self, x):
        x = self.conv1(x)
        x = self.bn1(x)
        x = x.view(x.size(0), -1)
        x = self.linear1(x)
        x = self.linear2(x)
        return x

# Instantiate the network
net = SimpleNet()

ARGS = {
    'net': net,
    'init_type': 'normal',
    'init_gain': 0.02,
    'gpu_ids': []
}
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 SimpleNet — a SimpleNet output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a SimpleNet 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
ssim Ran
ran; our contract draft was wrong, not the code
hitrainer/eavsr/models/.ipynb_checkpoints/losses-checkpoint.py
code served (permissive licence) · get_code("9151c793f90473f0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn.functional as F
from torch.autograd import Variable
from math import exp

torch.manual_seed(0)

def gaussian(window_size, sigma):
    gauss = torch.Tensor([exp(-(x - window_size // 2) ** 2 / float(2 * sigma ** 2)) for x in range(window_size)])
    return gauss / gauss.sum()

def create_window(window_size, channel):
    _1D_window = gaussian(window_size, 1.5).unsqueeze(1)
    _2D_window = _1D_window.mm(_1D_window.t()).float().unsqueeze(0).unsqueeze(0)
    window = Variable(_2D_window.expand(channel, 1, window_size, window_size).contiguous())
    return window

def _ssim(img1, img2, window, window_size, channel, size_average=True):
    mu1 = F.conv2d(img1, window, padding=window_size // 2, groups=channel)
    mu2 = F.conv2d(img2, window, padding=window_size // 2, groups=channel)
    mu1_sq = mu1.pow(2)
    mu2_sq = mu2.pow(2)
    mu1_mu2 = mu1 * mu2
    sigma1_sq = F.conv2d(img1 * img1, window, padding=window_size // 2, groups=channel) - mu1_sq
    sigma2_sq = F.conv2d(img2 * img2, window, padding=window_size // 2, groups=channel) - mu2_sq
    sigma12 = F.conv2d(img1 * img2, window, padding=window_size // 2, groups=channel) - mu1_mu2
    C1 = 0.01 ** 2
    C2 = 0.03 ** 2
    ssim_map = (2 * mu1_mu2 + C1) * (2 * sigma12 + C2) / ((mu1_sq + mu2_sq + C1) * (sigma1_sq + sigma2_sq + C2))
    if size_average:
        return ssim_map.mean()
    else:
        return ssim_map.mean(1).mean(1).mean(1)

def ssim(img1, img2, window_size=11, size_average=True):
    _, channel, _, _ = img1.size()
    window = create_window(window_size, channel)
    if img1.is_cuda:
        window = window.cuda(img1.get_device())
    window = window.type_as(img1)
    return _ssim(img1, img2, window, window_size, channel, size_average)

# Create test tensors with shape [batch=2, channels=3, height=4, width=5]
img1 = torch.randn(2, 3, 4, 5)
img2 = torch.randn(2, 3, 4, 5)

ARGS = {
    "img1": img1,
    "img2": img2,
    "window_size": 11,
    "size_average": 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 Tensor, 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
ssim Ran
ran; our contract draft was wrong, not the code
hitrainer/eavsr/models/losses.py
pointer only (licence: MIT); the stored copy get_code serves, from cszhilu1998/BracketIRE, is pointer only (licence: NOASSERTION) · get_code("70bb6d6f654b09a2")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from cszhilu1998/BracketIRE, and GitHub could not classify the licence of that repository (NOASSERTION). 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.

calc_lpips Not yet run
unverified (harvested, no recorded run)
hitrainer/eavsr/psnr_total.py
code served (permissive licence) · get_code("bdd8252839b9c504")
How it ran

no invocation recorded.

get_backwarp Not yet run
unverified (harvested, no recorded run)
hitrainer/eavsr/models/spy_net.py
code served (permissive licence) · get_code("50472aedac8d3cbd")
How it ran

no invocation recorded.

lpips_norm Not yet run
unverified (harvested, no recorded run)
hitrainer/eavsr/psnr_total.py
code served (permissive licence) · get_code("0da219b9bbf3d188")
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 15 distinct functions with an identity, 7 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 6 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
gaussian 160 other papers
32 dated earlier, 127 later, 1 same year, order not determinable · 7 only as an assembly brick
1812.11941 (2018-12)
High Quality Monocular Depth Estimation via Transfer Learning
1904.01538 (2019-04)
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
1907.11628 (2019-07)
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
and 157 more not named here
create_window 52 other papers
18 dated earlier, 34 later · 5 only as an assembly brick
1904.01538 (2019-04)
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
1907.11628 (2019-07)
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
2002.11616 (2020-02)
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
and 49 more not named here
ssim 28 other papers
7 dated earlier, 21 later
1904.01538 (2019-04)
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset
1907.11628 (2019-07)
Unsupervised Learning for Optical Flow Estimation Using Pyramid Convolution LSTM
2002.11616 (2020-02)
Zooming Slow-Mo: Fast and Accurate One-Stage Space-Time Video Super-Resolution
and 25 more not named here
diff_x 2 other papers
2 later
2309.11847 (2023-09)
MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion
2407.12511 (2024-07)
Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representations
diff_y 2 other papers
2 later
2309.11847 (2023-09)
MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion
2407.12511 (2024-07)
Fast Context-Based Low-Light Image Enhancement via Neural Implicit Representations
flow_warp 1 other paper
1 dated earlier
2208.03012 (2022-08)
Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution
init_net 1 other paper
1 later
2310.01840 (2023-10)
Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes

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 super-resolution (VSR) aiming to reconstruct a high-resolution (HR) video from its low-resolution (LR) counterpart has made tremendous progress in recent years. However, it remains challenging to deploy existing VSR methods to real-world data with complex degradations. On the one hand, there are few well-aligned real-world VSR datasets, especially with large super-resolution scale factors, which limits the development of real-world VSR tasks. On the other hand, alignment algorithms in existing VSR methods perform poorly for real-world videos, leading to unsatisfactory results. As an attempt to address the aforementioned issues, we build a real-world 4 VSR dataset, namely MVSR4$\times$, where low- and high-resolution videos are captured with different focal length lenses of a smartphone, respectively. Moreover, we propose an effective alignment method for real-world VSR, namely EAVSR. EAVSR takes the proposed multi-layer adaptive spatial transform network (MultiAdaSTN) to refine the offsets provided by the pre-trained optical flow estimation network. Experimental results on RealVSR and MVSR4$\times$ datasets show the effectiveness and practicality of our method, and we achieve state-of-the-art performance in real-world VSR task. The dataset and code will be publicly available.

For agents

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

get_harvested_code_for_paper("2212.05342")
get_code_for_paper("2212.05342")
have("2212.05342")

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

curl https://syntology.ai/api/ran/2212.05342.json

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

[![Syntology run record](https://syntology.ai/api/ran/2212.05342.svg)](https://syntology.ai/paper/2212.05342)

Connect an agent — have() is free.