SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2412.01427 · 2024

FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration

arXiv · PDF · Open in the Atlas

Code that ran

21 of 24 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; 3 honoured the contract we drafted, 2 violated it and 3 have no contract verdict; 13 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/2412.01427.json · badge: /api/ran/2412.01427.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
House-Leo/FoundIR community (classifier label)
classifier basis not recorded on the link
21 ran · 3 no recorded run
FunctionStatusWhere it lives
calculate_fid Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
House-Leo/FoundIR/metrics/fid.py
code served (permissive licence) · get_code("1d7ce6d6dd7ff5c1")
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 float64, ndim 0, 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 numpy as np
from scipy import linalg

np.random.seed(0)

# Create small test matrices for FID calculation
# Using dimension 4 for feature space
feature_dim = 4

# Generate sample means (1D arrays of shape (4,))
mu1 = np.random.randn(feature_dim).astype(np.float32)
mu2 = np.random.randn(feature_dim).astype(np.float32)

# Generate covariance matrices (4x4 positive semi-definite matrices)
# Create them from random data to ensure they're positive semi-definite
A1 = np.random.randn(feature_dim, feature_dim).astype(np.float32)
sigma1 = (A1 @ A1.T) + np.eye(feature_dim) * 0.1

A2 = np.random.randn(feature_dim, feature_dim).astype(np.float32)
sigma2 = (A2 @ A2.T) + np.eye(feature_dim) * 0.1

ARGS = {
    'mu1': mu1,
    'sigma1': sigma1,
    'mu2': mu2,
    'sigma2': sigma2,
    'eps': 1e-06
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
calculate_weights_indices Ran
ran; our contract draft was wrong, not the code
House-Leo/FoundIR/matlab_functions.py
pointer only (licence: MIT); the stored copy get_code serves, from QMoQ/OAPT, is pointer only (licence: NONE) · get_code("a0a9dee5557b1557")
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 QMoQ/OAPT, and GitHub detected no licence in that repository when it was checked. 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.

compute_feature Ran
ran, honoured the contract we drafted
House-Leo/FoundIR/metrics/niqe.py
code served (permissive licence) · get_code("5170ff1c4106b27a")
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 list, ndim 1, 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 numpy as np
from scipy.special import gamma

# Create a small 2D image block for testing
# The function expects a 2D ndarray that will be flattened
block = np.random.randn(4, 3).astype(np.float32)

# Ensure we have both positive and negative values for the computation
block[0, 0] = -2.5
block[1, 1] = 3.2
block[2, 2] = -1.1
block[3, 0] = 1.8

ARGS = {
    'block': block
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
cubic Ran
ran; our contract draft was wrong, not the code
House-Leo/FoundIR/matlab_functions.py
pointer only (licence: MIT); the stored copy get_code serves, from QMoQ/OAPT, is pointer only (licence: NONE) · get_code("2a78a7db11a55ede")
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 QMoQ/OAPT, and GitHub detected no licence in that repository when it was checked. 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.

default Ran
ran, violated the contract we drafted
House-Leo/FoundIR/src/model.py
code served (permissive licence) · get_code("d1ef6b8cb9a28a53")
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 str. 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

torch.manual_seed(0)

def exists(x):
    return x is not None

def default(val, d):
    if exists(val):
        return val
    return d() if callable(d) else d

# Test case 1: val is not None, should return val
val_1 = "test_value"
d_1 = lambda: "default_value"

# Test case 2: val is None, d is callable, should return d()
val_2 = None
d_2 = lambda: "computed_default"

# Test case 3: val is None, d is not callable, should return d
val_3 = None
d_3 = "static_default"

# Test case 4: val is a number
val_4 = 42
d_4 = 100

# Test case 5: val is a tensor
val_5 = torch.tensor([1.0, 2.0, 3.0])
d_5 = lambda: torch.tensor([0.0])

ARGS = {
    "val": val_1,
    "d": d_1
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
dict2str Ran
ran on a synthesized input
House-Leo/FoundIR/cal_metrics.py
code served (permissive licence) · get_code("aca6d1049c83a507")
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 str. 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 numpy as np

torch.manual_seed(0)

# Simple nested dictionary with various types
opt = {
    'model_name': 'resnet50',
    'learning_rate': 0.001,
    'batch_size': 32,
    'training': {
        'epochs': 100,
        'optimizer': 'adam',
        'loss': {
            'type': 'cross_entropy',
            'weight': 0.5
        }
    },
    'data': {
        'path': '/data/images',
        'augmentation': True
    }
}

ARGS = {
    'opt': opt,
    'indent': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
estimate_aggd_param Ran
ran, honoured the contract we drafted
House-Leo/FoundIR/metrics/niqe.py
code served (permissive licence) · get_code("a1282a48b0941f5d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, 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 numpy as np

# Create a small 2D image block with varied values
# The function flattens it, so shape doesn't matter too much
# but we want some negative and positive values for the calculations
block = np.array([
    [-2.5, -1.3, 0.8, 1.2],
    [-0.5, 0.3, 2.1, -1.8]
], dtype=np.float64)

ARGS = {
    'block': block
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
exists Ran
ran, violated the contract we drafted
House-Leo/FoundIR/src/model.py
code served (permissive licence) · get_code("608e364a9d2376a3")
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 bool, ndim 0, dtype family float, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

def exists(x):
    return x is not None

ARGS = {
    "x": torch.tensor([1, 2, 3, 4])
}
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 bool, ndim 0, dtype family float, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
extract_inception_features Ran
ran, honoured the contract we drafted
House-Leo/FoundIR/metrics/fid.py
code served (permissive licence) · get_code("c9fb213c957dc82d")
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 2, dtype family float, shape (6, 128) 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 as nn

torch.manual_seed(0)

# Create a minimal Inception model that returns a tuple with features
class MinimalInception(nn.Module):
    def __init__(self):
        super().__init__()
        self.conv = nn.Conv2d(3, 8, kernel_size=3, padding=1)
    
    def forward(self, x):
        # Return tuple where first element is the feature tensor
        features = self.conv(x)
        return (features,)

# Create a data generator that yields batches
def data_generator():
    for _ in range(3):
        # Yield tensors of shape (2, 3, 4, 4) - batch of 2, 3 channels, 4x4 spatial
        yield torch.randn(2, 3, 4, 4)

# Build the arguments
inception_model = MinimalInception()
gen = data_generator()

ARGS = {
    'data_generator': gen,
    'inception': inception_model,
    'len_generator': 3,
    'device': 'cpu'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (6, 128) — shape (6, 128) 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
House-Leo/FoundIR/specialist_model/basicsr/archs/arch_util.py
code served (permissive licence) · get_code("ef9faf68f492a375")
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 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 optical flow tensor: (batch=2, height=3, width=5, 2)
# The flow represents displacement in (x, y) directions
flow = torch.randn(2, 3, 5, 2) * 0.5  # Small displacements

ARGS = {
    'x': x,
    'flow': flow,
    'interp_mode': 'bilinear',
    'padding_mode': 'zeros',
    'align_corners': True,
}
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 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
img2tensor Ran
ran on a synthesized input
House-Leo/FoundIR/cal_metrics.py
code served (permissive licence) · get_code("101e90f511df891e")
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 3, dtype family float, shape (3, 4, 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 cv2
import torch
import numpy as np

torch.manual_seed(0)

# Create a small BGR image (height=4, width=3, channels=3)
img_bgr = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)

# Create a list of two small BGR images for testing list input
imgs_list = [
    np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8),
    np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
]

ARGS = {
    'imgs': img_bgr,
    'bgr2rgb': True,
    'float32': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (3, 4, 3) — shape (3, 4, 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
imresize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
House-Leo/FoundIR/matlab_functions.py
code served (permissive licence) · get_code("dfb4171d25811492")
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 3, dtype family float, shape (3, 8, 10) 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 numpy as np
import math

torch.manual_seed(0)

# Create a small test image tensor with shape (c, h, w)
# Using distinct sizes: 3 channels, 4 height, 5 width
img_tensor = torch.rand(3, 4, 5)

# Also create a numpy version to test that code path
img_numpy = np.random.rand(4, 5, 3)

ARGS = {
    "img": img_tensor,
    "scale": 2.0,
    "antialiasing": True,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (3, 8, 10) — shape (3, 8, 10) 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
make_layer Ran
ran; our contract draft was wrong, not the code
House-Leo/FoundIR/specialist_model/basicsr/archs/arch_util.py
code served (permissive licence) · get_code("96ad5dc9ca239aec")
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)

# Define a simple basic block that can be instantiated with **kwarg
class SimpleBasicBlock(nn.Module):
    def __init__(self, in_channels=3, out_channels=4):
        super().__init__()
        self.conv = nn.Conv2d(in_channels, out_channels, kernel_size=3, padding=1)
    
    def forward(self, x):
        return self.conv(x)

# Construct the arguments
ARGS = {
    'basic_block': SimpleBasicBlock,
    'num_basic_block': 3,
    'in_channels': 3,
    'out_channels': 4
}
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
prepare_for_ssim Ran
ran; our contract draft was wrong, not the code
House-Leo/FoundIR/metrics/psnr_ssim.py
pointer only (licence: MIT); the stored copy get_code serves, from AlifAshrafee/Restoring-Without-Forgetting, is pointer only (licence: NONE) · get_code("95c6eba9350a455a")
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 AlifAshrafee/Restoring-Without-Forgetting, and GitHub detected no licence in that repository when it was checked. 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.

prepare_for_ssim_rgb Ran
ran; our contract draft was wrong, not the code
House-Leo/FoundIR/metrics/psnr_ssim.py
pointer only (licence: MIT); the stored copy get_code serves, from AlifAshrafee/Restoring-Without-Forgetting, is pointer only (licence: NONE) · get_code("fb93712db7064ac4")
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 AlifAshrafee/Restoring-Without-Forgetting, and GitHub detected no licence in that repository when it was checked. 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.

reorder_image Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
House-Leo/FoundIR/metrics/metric_util.py
pointer only (licence: MIT); the stored copy get_code serves, from AlifAshrafee/Restoring-Without-Forgetting, is pointer only (licence: NONE) · get_code("95067518dc16b3e5")
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 AlifAshrafee/Restoring-Without-Forgetting, and GitHub detected no licence in that repository when it was checked. 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.

resize_flow Ran
ran; our contract draft was wrong, not the code
House-Leo/FoundIR/specialist_model/basicsr/archs/arch_util.py
pointer only (licence: MIT); the stored copy get_code serves, from JiaxiaoWang/EvReflection, is pointer only (licence: NONE) · get_code("5a1d8458dc7077a6")
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 JiaxiaoWang/EvReflection, and GitHub detected no licence in that repository when it was checked. 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.

scandir Ran
ran on a synthesized input
House-Leo/FoundIR/cal_metrics.py
code served (permissive licence) · get_code("7952dbdafdde6e7a")
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 generator. 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 os
import tempfile
import shutil

# Create a temporary directory structure for testing
temp_dir = tempfile.mkdtemp()

# Create some test files with different suffixes
os.makedirs(os.path.join(temp_dir, "subdir"), exist_ok=True)
open(os.path.join(temp_dir, "file1.txt"), "w").close()
open(os.path.join(temp_dir, "file2.py"), "w").close()
open(os.path.join(temp_dir, ".hidden.txt"), "w").close()
open(os.path.join(temp_dir, "subdir", "file3.txt"), "w").close()
open(os.path.join(temp_dir, "subdir", "file4.py"), "w").close()

ARGS = {
    "dir_path": temp_dir,
    "suffix": ".txt",
    "recursive": False,
    "full_path": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type generator — a generator output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a generator 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
tensor2img Ran
ran; our contract draft was wrong, not the code
House-Leo/FoundIR/src/model.py
code served (permissive licence) · get_code("ac6cfb6f7e2c39d2")
How it ran

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

import torch
import numpy as np

torch.manual_seed(0)

# Case 1: 3D tensor (3 x H x W) - most common case
tensor_3d = torch.rand(3, 4, 5)

# Case 2: 4D tensor (B x 3 x H x W) - batch of images
tensor_4d = torch.rand(2, 3, 4, 5)

# Case 3: 2D tensor (H x W) - grayscale single image
tensor_2d = torch.rand(4, 5)

# Case 4: List of tensors
tensor_list = [torch.rand(3, 4, 5), torch.rand(1, 4, 5)]

ARGS = {
    'tensor': tensor_3d,
    'rgb2bgr': True,
    'out_type': np.uint8,
    'min_max': (0, 1)
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, torch, torchvision — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (4, 5, 3) — shape (4, 5, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
to_3d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
House-Leo/FoundIR/specialist_model/basicsr/archs/Restormer_arch.py
pointer only (licence: MIT); the stored copy get_code serves, from gladzhang/Xformer, is pointer only (licence: NONE) · get_code("82a15cc1e46f7e4d")
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 gladzhang/Xformer, and GitHub detected no licence in that repository when it was checked. 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.

to_4d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
House-Leo/FoundIR/specialist_model/basicsr/archs/Restormer_arch.py
pointer only (licence: MIT); the stored copy get_code serves, from gladzhang/Xformer, is pointer only (licence: NONE) · get_code("b20f2a5df739a59e")
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 gladzhang/Xformer, and GitHub detected no licence in that repository when it was checked. 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.

check_image_size Not yet run
unverified (harvested, no recorded run)
House-Leo/FoundIR/specialist_model/inference_lowlight.py
pointer only (licence: MIT); the stored copy get_code serves, from supersupercong/uhdformer, is pointer only (licence: NOASSERTION) · get_code("7ab32da4188a2275")
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 supersupercong/uhdformer, 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. No invocation recorded.

check_image_size Not yet run
unverified (harvested, no recorded run)
House-Leo/FoundIR/specialist_model/inference_weather.py
code served (permissive licence) · get_code("3d48eb1a78a327d1")
How it ran

no invocation recorded.

niqe Not yet run
unverified (harvested, no recorded run)
House-Leo/FoundIR/metrics/niqe.py
code served (permissive licence) · get_code("0029cb1566e47350")
How it ran

no invocation recorded.

Also present in other papers' code

Of 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 20 are also present in other papers whose code we hold (20 with at least one paper dated earlier, 2 the same month, 10 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
exists 144 other papers
108 dated earlier, 4 the same month, 27 later, 5 same year, order not determinable · 40 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
1711.11585 (2017-11)
High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
and 141 more not named here
to_3d 80 other papers
62 dated earlier, 16 later, 2 same year, order not determinable · 18 only as an assembly brick
2003.06792 (2020-03)
Learning Enriched Features for Real Image Restoration and Enhancement
2102.02808 (2021-02)
Multi-Stage Progressive Image Restoration
2111.09881 (2021-11)
Restormer: Efficient Transformer for High-Resolution Image Restoration
and 77 more not named here
default 79 other papers
57 dated earlier, 3 the same month, 16 later, 3 same year, order not determinable · 15 only as an assembly brick
1611.07004 (2016-11)
Image-to-Image Translation with Conditional Adversarial Networks
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
and 76 more not named here
to_4d 79 other papers
61 dated earlier, 16 later, 2 same year, order not determinable · 18 only as an assembly brick
2003.06792 (2020-03)
Learning Enriched Features for Real Image Restoration and Enhancement
2102.02808 (2021-02)
Multi-Stage Progressive Image Restoration
2111.09881 (2021-11)
Restormer: Efficient Transformer for High-Resolution Image Restoration
and 76 more not named here
make_layer 29 other papers
21 dated earlier, 7 later, 1 same year, order not determinable
2107.10833 (2021-07)
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
2108.11048 (2021-08)
Memory-Augmented Non-Local Attention for Video Super-Resolution
and 26 more not named here
flow_warp 25 other papers
17 dated earlier, 7 later, 1 same year, order not determinable · 1 only as an assembly brick
2107.10833 (2021-07)
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
2303.06373 (2023-03)
Recursive Generalization Transformer for Image Super-Resolution
and 22 more not named here
resize_flow 21 other papers
14 dated earlier, 6 later, 1 same year, order not determinable
2107.10833 (2021-07)
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
2303.06373 (2023-03)
Recursive Generalization Transformer for Image Super-Resolution
and 18 more not named here
reorder_image 17 other papers
13 dated earlier, 3 later, 1 same year, order not determinable
2204.04676 (2022-04)
Simple Baselines for Image Restoration
2303.06373 (2023-03)
Recursive Generalization Transformer for Image Super-Resolution
and 14 more not named here
calculate_fid 8 other papers
8 dated earlier
2204.04676 (2022-04)
Simple Baselines for Image Restoration
2303.02881 (2023-03)
KBNet: Kernel Basis Network for Image Restoration
2308.14036 (2023-08)
MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing
and 5 more not named here
estimate_aggd_param 8 other papers
8 dated earlier
2204.04676 (2022-04)
Simple Baselines for Image Restoration
Chao_Equivalent_Transformation_and_Dual_Stream_Network_Construction_for_Mobile_Image_CVPR_2023_paper (2023 (year only))
Equivalent Transformation and Dual Stream Network Construction for Mobile Image Super-Resolution
and 5 more not named here
extract_inception_features 8 other papers
8 dated earlier
2204.04676 (2022-04)
Simple Baselines for Image Restoration
2303.02881 (2023-03)
KBNet: Kernel Basis Network for Image Restoration
2308.14036 (2023-08)
MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing
and 5 more not named here
prepare_for_ssim 8 other papers
6 dated earlier, 2 later
ijcai2022_0131 (2022 (year only))
Exploring Fourier Prior for Single Image Rain Removal
2204.04676 (2022-04)
Simple Baselines for Image Restoration
and 5 more not named here
compute_feature 7 other papers
7 dated earlier
2204.04676 (2022-04)
Simple Baselines for Image Restoration
2308.14036 (2023-08)
MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing
and 4 more not named here
niqe 7 other papers
7 dated earlier
2204.04676 (2022-04)
Simple Baselines for Image Restoration
2308.14036 (2023-08)
MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing
and 4 more not named here
cubic 5 other papers
5 dated earlier
1809.00219 (2018-09)
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
2405.04312 (2024-05)
Inf-DiT: Upsampling Any-Resolution Image with Memory-Efficient Diffusion Transformer
2405.09873 (2024-05)
IRSRMamba: Infrared Image Super-Resolution via Mamba-based Wavelet Transform Feature Modulation Model
and 2 more not named here
prepare_for_ssim_rgb 5 other papers
3 dated earlier, 2 later
ijcai2022_0131 (2022 (year only))
Exploring Fourier Prior for Single Image Rain Removal
2405.03349 (2024-05)
Retinexmamba: Retinex-based Mamba for Low-light Image Enhancement
2409.01274 (2024-09)
DAVIDE: Depth-Aware Video Deblurring
and 2 more not named here
tensor2img 3 other papers
3 dated earlier
2309.03020 (2023-09)
SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution
2401.05907 (2024-01)
Efficient Image Deblurring Networks based on Diffusion Models
2407.13987 (2024-07)
RealViformer: Investigating Attention for Real-World Video Super-Resolution
calculate_weights_indices 2 other papers
2 dated earlier
2406.00629 (2024-06)
Correlation Matching Transformation Transformers for UHD Image Restoration
2408.11480 (2024-08)
OAPT: Offset-Aware Partition Transformer for Double JPEG Artifacts Removal
check_image_size 1 other paper
1 dated earlier
2406.00629 (2024-06)
Correlation Matching Transformation Transformers for UHD Image Restoration
imresize 1 other paper
1 dated earlier
2406.00629 (2024-06)
Correlation Matching Transformation Transformers for UHD Image Restoration

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

Despite the significant progress made by all-in-one models in universal image restoration, existing methods suffer from a generalization bottleneck in real-world scenarios, as they are mostly trained on small-scale synthetic datasets with limited degradations. Therefore, large-scale high-quality real-world training data is urgently needed to facilitate the emergence of foundational models for image restoration. To advance this field, we spare no effort in contributing a million-scale dataset with two notable advantages over existing training data: real-world samples with larger-scale, and degradation types with higher diversity. By adjusting internal camera settings and external imaging conditions, we can capture aligned image pairs using our well-designed data acquisition system over multiple rounds and our data alignment criterion. Moreover, we propose a robust model, FoundIR, to better address a broader range of restoration tasks in real-world scenarios, taking a further step toward foundation models. Specifically, we first utilize a diffusion-based generalist model to remove degradations by learning the degradation-agnostic common representations from diverse inputs, where incremental learning strategy is adopted to better guide model training. To refine the model's restoration capability in complex scenarios, we introduce degradation-aware specialist models for achieving final high-quality results. Extensive experiments show the value of our dataset and the effectiveness of our method.

For agents

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

get_harvested_code_for_paper("2412.01427")
get_code_for_paper("2412.01427")
have("2412.01427")

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

curl https://syntology.ai/api/ran/2412.01427.json

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

[![Syntology run record](https://syntology.ai/api/ran/2412.01427.svg)](https://syntology.ai/paper/2412.01427)

Connect an agent — have() is free.