SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2004.09484 · 2020

Bringing Old Photos Back to Life

arXiv · PDF · Open in the Atlas

Code that ran

25 of 31 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; 1 honoured the contract we drafted, 1 violated it and 21 have no contract verdict; 2 failures of our instrument; 6 no recorded run), measured 2026-11-21; 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/2004.09484.json · badge: /api/ran/2004.09484.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
microsoft/Bringing-Old-Photos-Back-to-Life canonical (classifier label)
classifier basis: census
9 ran · 2 no recorded run
yasamin-niknam/Image-Restoration community (classifier label)
classifier basis not recorded on the link
5 ran · 3 no recorded run
random-zhang/Bringing-Old-Photos-Back-to-Life-master community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
Nero-Disney/MICROSOFT_Bringing-Old-Photos-Back-to-Life community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
shinde-Pratik/Image-Restoration community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
ImportPaddle/Old2Life community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
SN Ran
ran on a synthesized input
Nero-Disney/MICROSOFT_Bringing-Old-Photos-Back-to-Life/Global/models/networks.py
pointer only (licence: MIT) · get_code("153d5982d4d954a0")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, Nero-Disney/MICROSOFT_Bringing-Old-Photos-Back-to-Life, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

calculate_cdf Ran
ran on a synthesized input
microsoft/Bringing-Old-Photos-Back-to-Life/Face_Detection/align_warp_back_multiple_dlib.py
code served (permissive licence) · get_code("4a26a6d6f969cd89")
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 1, dtype family float, shape (4,) 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)

# The function expects a histogram array-like object that supports:
# - .cumsum() method
# - .max() method
# These are numpy array or torch tensor methods

# Create a small histogram as a numpy array
histogram = np.array([1.0, 2.0, 3.0, 4.0])

ARGS = {
    "histogram": histogram
}
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 ndarray, ndim 1, dtype family float, shape (4,) — shape (4,) 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
calculate_cdf Ran
ran on a synthesized input
random-zhang/Bringing-Old-Photos-Back-to-Life-master/Face_Detection/align_warp_back_multiple_dlib.py
pointer only (licence: MIT) · get_code("501d7f5d4d8446fe")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, random-zhang/Bringing-Old-Photos-Back-to-Life-master, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

calculate_lookup Ran
ran on a synthesized input
random-zhang/Bringing-Old-Photos-Back-to-Life-master/Face_Detection/align_warp_back_multiple_dlib.py
pointer only (licence: MIT) · get_code("30334876eaff2b54")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, random-zhang/Bringing-Old-Photos-Back-to-Life-master, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

compute_transformation_matrix Ran
ran on a synthesized input
microsoft/Bringing-Old-Photos-Back-to-Life/Face_Detection/detect_all_dlib.py
code served (permissive licence) · get_code("eedfdee5e134b45c")
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 2, dtype family float, shape (3, 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 numpy as np
from skimage.transform import SimilarityTransform

# Create a small test image (height=256, width=256, channels=3)
img = np.random.rand(256, 256, 3).astype(np.float32)

# Create landmarks - 5 facial landmarks with (x, y) coordinates
# These should be in pixel coordinates matching the image dimensions
landmark = np.array([
    [128.0, 113.0],   # landmark 1
    [158.0, 113.0],   # landmark 2
    [143.0, 143.0],   # landmark 3
    [110.0, 180.2],   # landmark 4
    [176.0, 180.2]    # landmark 5
], dtype=np.float32)

# normalize parameter
normalize = False

# target_face_scale parameter
target_face_scale = 1.0

ARGS = {
    'img': img,
    'landmark': landmark,
    'normalize': normalize,
    'target_face_scale': target_face_scale
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (3, 3) — shape (3, 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
compute_transformation_matrix Ran
ran on a synthesized input
microsoft/Bringing-Old-Photos-Back-to-Life/Face_Detection/detect_all_dlib_HR.py
code served (permissive licence) · get_code("1b91380589fe7dba")
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 2, dtype family float, shape (3, 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 numpy as np
from skimage.transform import SimilarityTransform

def _standard_face_pts():
    pts = np.array([196.0, 226.0, 316.0, 226.0, 256.0, 286.0, 220.0, 360.4, 292.0, 360.4], np.float32) / 256.0 - 1.0
    return np.reshape(pts, (5, 2))

def compute_transformation_matrix(img, landmark, normalize, target_face_scale=1.0):
    std_pts = _standard_face_pts()
    target_pts = (std_pts * target_face_scale + 1) / 2 * 512.0
    h, w, c = img.shape
    if normalize == True:
        landmark[:, 0] = landmark[:, 0] / h * 2 - 1.0
        landmark[:, 1] = landmark[:, 1] / w * 2 - 1.0
    affine = SimilarityTransform()
    affine.estimate(target_pts, landmark)
    return affine.params

# Create a small image with shape (h, w, c)
img = np.random.rand(256, 512, 3).astype(np.float32)

# Create landmark points (5 points, 2 coordinates each)
landmark = np.array([
    [100.0, 150.0],
    [200.0, 150.0],
    [150.0, 200.0],
    [120.0, 250.0],
    [180.0, 250.0]
], dtype=np.float32)

# normalize flag
normalize = False

# target_face_scale parameter
target_face_scale = 1.0

ARGS = {
    "img": img,
    "landmark": landmark,
    "normalize": normalize,
    "target_face_scale": target_face_scale
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, skimage — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (3, 3) — shape (3, 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
compute_transformation_matrix Ran
ran on a synthesized input
random-zhang/Bringing-Old-Photos-Back-to-Life-master/Face_Detection/detect_all_dlib.py
pointer only (licence: MIT) · get_code("ba751f4f15abd9e3")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, random-zhang/Bringing-Old-Photos-Back-to-Life-master, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

copyconf Ran
ran on a synthesized input
shinde-Pratik/Image-Restoration/Face_Enhancement/util/util.py
pointer only (licence: MIT) · get_code("700b6c26b9f820a8")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, shinde-Pratik/Image-Restoration, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

data_transforms Ran
ran on a synthesized input
microsoft/Bringing-Old-Photos-Back-to-Life/Global/detection.py
code served (permissive licence) · get_code("448ee449b8b97680")
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 Image. 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.

from PIL import Image
import numpy as np

# Create a small test image
img_array = np.random.randint(0, 256, (480, 640, 3), dtype=np.uint8)
img = Image.fromarray(img_array)

# Define arguments for data_transforms function
ARGS = {
    'img': img,
    'full_size': 'full_size',
    'method': Image.BICUBIC
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Image — a Image output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Image output the recorded ndim 3 and dtype family int 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
data_transforms Ran
ran on a synthesized input
ImportPaddle/Old2Life/Global/detection.py
pointer only (licence: MIT) · get_code("ff2a8f34a4a25058")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, ImportPaddle/Old2Life, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

data_transforms Ran
ran on a synthesized input
Nero-Disney/MICROSOFT_Bringing-Old-Photos-Back-to-Life/Global/detection.py
pointer only (licence: MIT) · get_code("40d3c46da7fced6c")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, Nero-Disney/MICROSOFT_Bringing-Old-Photos-Back-to-Life, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

data_transforms Ran
ran on a synthesized input
yasamin-niknam/Image-Restoration/Global/detection.py
pointer only (licence: MIT) · get_code("a40025053b8b9874")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yasamin-niknam/Image-Restoration, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

default_loader Ran
ran, honoured the contract we drafted
yasamin-niknam/Image-Restoration/Face_Enhancement/data_FE/image_folder.py
pointer only (licence: MIT); the stored copy get_code serves, from xlgsyzp/cvpt, is pointer only (licence: NONE) · get_code("ac269a0e4b8d946e")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yasamin-niknam/Image-Restoration, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

getPSNR Ran
ran on a synthesized input
yasamin-niknam/Image-Restoration/calc_corr_score.py
pointer only (licence: MIT) · get_code("e8a3bd56ec0d4924")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yasamin-niknam/Image-Restoration, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

get_landmark Ran
ran on a synthesized input
microsoft/Bringing-Old-Photos-Back-to-Life/Face_Detection/detect_all_dlib.py
code served (permissive licence) · get_code("ed01603c6098e7fe")
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 torch
import numpy as np

class MockLandmarkPart:
    def __init__(self, x, y):
        self.x = x
        self.y = y

class MockFaceLandmarks:
    def __init__(self):
        self.parts_data = {
            0: MockLandmarkPart(100.5, 200.3),
            1: MockLandmarkPart(150.2, 180.7),
            2: MockLandmarkPart(120.8, 220.1),
        }
    
    def part(self, id):
        return self.parts_data[id]

face_landmarks = MockFaceLandmarks()
landmark_id = 0

ARGS = {
    "face_landmarks": face_landmarks,
    "id": landmark_id,
}
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 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
get_norm_layer Ran
ran on a synthesized input
Nero-Disney/MICROSOFT_Bringing-Old-Photos-Back-to-Life/Global/models/networks.py
pointer only (licence: MIT) · get_code("6b6192bdc8ac55fe")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, Nero-Disney/MICROSOFT_Bringing-Old-Photos-Back-to-Life, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

get_pad_layer Ran
ran; our contract draft was wrong, not the code
microsoft/Bringing-Old-Photos-Back-to-Life/Global/detection_models/antialiasing.py
pointer only (licence: MIT); the stored copy get_code serves, from linwei-chen/seg-aliasing, is pointer only (licence: NONE) · get_code("50aa4a59fe718c61")
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 linwei-chen/seg-aliasing, 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.

is_image_file Ran
ran, violated the contract we drafted
yasamin-niknam/Image-Restoration/Face_Enhancement/data_FE/image_folder.py
pointer only (licence: MIT) · get_code("e559cb5e8a6388f6")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yasamin-niknam/Image-Restoration, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

load_obj Ran
ran; our contract draft was wrong, not the code
shinde-Pratik/Image-Restoration/Face_Enhancement/util/util.py
pointer only (licence: MIT) · get_code("30d56fdfbf93d0d3")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, shinde-Pratik/Image-Restoration, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

make_dataset Ran
ran on a synthesized input
yasamin-niknam/Image-Restoration/Face_Enhancement/data_FE/image_folder.py
pointer only (licence: MIT) · get_code("bc148d83b0f09939")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yasamin-niknam/Image-Restoration, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

match_histograms Ran
ran on a synthesized input
microsoft/Bringing-Old-Photos-Back-to-Life/Face_Detection/align_warp_back_multiple_dlib.py
code served (permissive licence) · get_code("5f538af2f6dc997a")
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, 3, 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 numpy as np
import cv2

# Create small test images (BGR format required by cv2)
# Source image: 4x3 pixels with BGR channels
src_image = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)

# Reference image: 5x3 pixels with BGR channels (different size to show distinction)
ref_image = np.random.randint(0, 256, (5, 3, 3), dtype=np.uint8)

ARGS = {
    "src_image": src_image,
    "ref_image": ref_image,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy — 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, 3, 3) — shape (4, 3, 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
match_histograms Ran
ran on a synthesized input
random-zhang/Bringing-Old-Photos-Back-to-Life-master/Face_Detection/align_warp_back_multiple_dlib.py
pointer only (licence: MIT) · get_code("971b7bb559205806")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, random-zhang/Bringing-Old-Photos-Back-to-Life-master, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

scale_tensor Ran
ran on a synthesized input
microsoft/Bringing-Old-Photos-Back-to-Life/Global/detection.py
code served (permissive licence) · get_code("cbc73e056f2fd52a")
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, 256, 384) 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 tensor with shape (batch, channels, height, width)
# Using batch=2, channels=3, height=8, width=12 for distinct dimensions
img_tensor = torch.randn(2, 3, 8, 12)

ARGS = {
    "img_tensor": img_tensor,
    "default_scale": 256
}
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, 256, 384) — shape (2, 3, 256, 384) 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
search Ran
ran on a synthesized input
microsoft/Bringing-Old-Photos-Back-to-Life/Face_Detection/detect_all_dlib.py
code served (permissive licence) · get_code("761a87b13ffc3dfb")
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 2, dtype family float; no output shape is stated. It ran in syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1) at 2026-09-27T00:55:05Z. 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

class MockLandmarkPart:
    def __init__(self, x, y):
        self.x = x
        self.y = y

class MockFaceLandmarks:
    def __init__(self):
        self.landmarks = {
            36: MockLandmarkPart(100.5, 150.2),
            39: MockLandmarkPart(120.3, 155.1),
            42: MockLandmarkPart(200.8, 152.4),
            45: MockLandmarkPart(220.2, 158.6),
            30: MockLandmarkPart(160.0, 200.0),
            48: MockLandmarkPart(130.5, 250.3),
            54: MockLandmarkPart(210.7, 248.9),
        }
    
    def part(self, id):
        return self.landmarks[id]

face_landmarks = MockFaceLandmarks()

ARGS = {
    "face_landmarks": face_landmarks
}
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 ndarray, ndim 2, dtype family float — no output shape is stated: no later run recorded an output shape for this sample (observed_output and metamorphic_properties carry none; shape_contract and output_contract record ndim only)
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 syntology-harvest-sandbox:v5-deps (sha256:6a292aa1aed1); 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
tensor2im Ran
ran on a synthesized input
shinde-Pratik/Image-Restoration/Face_Enhancement/util/util.py
pointer only (licence: MIT) · get_code("9ba5e300297925fe")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, shinde-Pratik/Image-Restoration, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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.

blend_mask Not yet run
unverified (harvested, no recorded run)
microsoft/Bringing-Old-Photos-Back-to-Life/Global/detection.py
code served (permissive licence) · get_code("052a0c14fc4aa169")
How it ran

no invocation recorded.

blend_mask Not yet run
unverified (harvested, no recorded run)
yasamin-niknam/Image-Restoration/Global/detection.py
pointer only (licence: MIT) · get_code("ad77605fdbcb472d")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yasamin-niknam/Image-Restoration, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

calculate_lookup Not yet run
unverified (harvested, no recorded run)
microsoft/Bringing-Old-Photos-Back-to-Life/Face_Detection/align_warp_back_multiple_dlib.py
code served (permissive licence) · get_code("3f6e5dbc6f26b22f")
How it ran

no invocation recorded.

create_model Not yet run
unverified (harvested, no recorded run)
Nero-Disney/MICROSOFT_Bringing-Old-Photos-Back-to-Life/Global/models/models.py
pointer only (licence: MIT) · get_code("4bf167308d919f53")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, Nero-Disney/MICROSOFT_Bringing-Old-Photos-Back-to-Life, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

irregular_hole_synthesize Not yet run
unverified (harvested, no recorded run)
yasamin-niknam/Image-Restoration/calc_corr_score.py
pointer only (licence: MIT) · get_code("f0068d0de544c123")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yasamin-niknam/Image-Restoration, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

save_image Not yet run
unverified (harvested, no recorded run)
yasamin-niknam/Image-Restoration/Global/detection.py
pointer only (licence: MIT) · get_code("8654915f0b73c3ed")
How it ran

The body of this sample is withheld: MIT, as GitHub detects it on this paper's repository, yasamin-niknam/Image-Restoration, is in the permissive set, but a licence decision keeps the body a pointer: the reason for that decision is not recorded with 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. No invocation recorded.

Also present in other papers' code

Of 31 samples lifted from this paper's linked repositories, 31 carry a function identity and 0 do not. Of the 26 distinct functions with an identity, 5 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 1 the same month, 4 later) and 21 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
is_image_file 62 other papers
12 dated earlier, 1 the same month, 49 later
1609.04802 (2016-09)
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
1703.07511 (2017-03)
Deep Photo Style Transfer
1710.10916 (2017-10)
StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks
and 59 more not named here
default_loader 27 other papers
10 dated earlier, 17 later
1710.03463 (2017-10)
Learning to Generalize: Meta-Learning for Domain Generalization
1803.08669 (2018-03)
Pyramid Stereo Matching Network
1810.11408 (2018-10)
Anytime Stereo Image Depth Estimation on Mobile Devices
and 24 more not named here
get_pad_layer 25 other papers
25 later · 3 only as an assembly brick
2007.15651 (2020-07)
Contrastive Learning for Unpaired Image-to-Image Translation
2008.09604 (2020-08)
Delving Deeper into Anti-aliasing in ConvNets
2111.03042 (2021-11)
Unsupervised Learning of Compositional Energy Concepts
and 22 more not named here
load_obj 3 other papers
1 dated earlier, 2 later
1908.08628 (2019-08)
Shadow Removal via Shadow Image Decomposition
2007.06286 (2020-07)
Beyond Graph Neural Networks with Lifted Relational Neural Networks
2207.05202 (2022-07)
The Cosmic Graph: Optimal Information Extraction from Large-Scale Structure using Catalogues
copyconf 1 other paper
1 dated earlier
1908.08628 (2019-08)
Shadow Removal via Shadow Image Decomposition

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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose to restore old photos that suffer from severe degradation through a deep learning approach. Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize. Therefore, we propose a novel triplet domain translation network by leveraging real photos along with massive synthetic image pairs. Specifically, we train two variational autoencoders (VAEs) to respectively transform old photos and clean photos into two latent spaces. And the translation between these two latent spaces is learned with synthetic paired data. This translation generalizes well to real photos because the domain gap is closed in the compact latent space. Besides, to address multiple degradations mixed in one old photo, we design a global branch with a partial nonlocal block targeting to the structured defects, such as scratches and dust spots, and a local branch targeting to the unstructured defects, such as noises and blurriness. Two branches are fused in the latent space, leading to improved capability to restore old photos from multiple defects. The proposed method outperforms state-of-the-art methods in terms of visual quality for old photos restoration.

For agents

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

get_harvested_code_for_paper("2004.09484")
get_code_for_paper("2004.09484")
have("2004.09484")

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

curl https://syntology.ai/api/ran/2004.09484.json

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

[![Syntology run record](https://syntology.ai/api/ran/2004.09484.svg)](https://syntology.ai/paper/2004.09484)

Connect an agent — have() is free.