SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.05650 · 2020

Invertible Image Rescaling

arXiv · PDF · Open in the Atlas

Code that ran

15 of 17 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; 5 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 1 failure of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2005.05650.json · badge: /api/ran/2005.05650.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
pkuxmq/Invertible-Image-Rescaling canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
JoegameZhou/ms-irn community (classifier label)
classifier basis not recorded on the link
8 ran · 1 no recorded run
andreasfloros/IRN community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
LCM1999/VolumeRescaling community (classifier label)
classifier basis not recorded on the link
1 ran · 1 no recorded run
FunctionStatusWhere it lives
calculate_psnr Ran
ran, honoured the contract we drafted
pkuxmq/Invertible-Image-Rescaling/metrics/calculate_PSNR_SSIM.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from redrock303/ADF-LLIE, is pointer only (licence: NONE) · get_code("9394ff2c25b8a988")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from redrock303/ADF-LLIE, 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.

calculate_ssim Ran
ran, honoured the contract we drafted
pkuxmq/Invertible-Image-Rescaling/metrics/calculate_PSNR_SSIM.py
code served (permissive licence) · get_code("5aef99e58703c44a")
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
import cv2

# Create two small test images with values in [0, 255]
# Using distinct sizes to allow shape probing
np.random.seed(0)

# Test case 1: 3D color image (height, width, channels)
img1_3d = np.random.randint(0, 256, size=(32, 32, 3), dtype=np.uint8)
img2_3d = np.random.randint(0, 256, size=(32, 32, 3), dtype=np.uint8)

# Test case 2: 2D grayscale image
img1_2d = np.random.randint(0, 256, size=(32, 32), dtype=np.uint8)
img2_2d = np.random.randint(0, 256, size=(32, 32), dtype=np.uint8)

# Test case 3: 3D single channel image
img1_single = np.random.randint(0, 256, size=(32, 32, 1), dtype=np.uint8)
img2_single = np.random.randint(0, 256, size=(32, 32, 1), dtype=np.uint8)

ARGS = {
    'img1': img1_3d,
    'img2': img2_3d,
}
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 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
count_parameters Ran
ran on a synthesized input
andreasfloros/IRN/utils.py
code served (permissive licence) · get_code("01aa7bd3d5f55770")
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 int, ndim 0, dtype family int, 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 as th
import torch.nn as nn

torch = th

torch.manual_seed(0)

class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear1 = nn.Linear(4, 3)
        self.linear2 = nn.Linear(3, 2)
    
    def forward(self, x):
        return self.linear2(self.linear1(x))

model = SimpleModel()

ARGS = {
    "model": model
}
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 int, ndim 0, dtype family int, 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
dict2str Ran
ran; our contract draft was wrong, not the code
JoegameZhou/ms-irn/src/options/options.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from liyuantsao/BFSR, is pointer only (licence: NONE) · get_code("40c52ad98161c17b")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from liyuantsao/BFSR, 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.

dict_to_nonedict Ran
ran on a synthesized input
JoegameZhou/ms-irn/src/options/options.py
code served (permissive licence) · get_code("f729c1e42588847e")
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 NoneDict. 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)

class NoneDict(dict):
    def __missing__(self, key):
        return None

def dict_to_nonedict(opt):
    if isinstance(opt, dict):
        new_opt = dict()
        for key, sub_opt in opt.items():
            new_opt[key] = dict_to_nonedict(sub_opt)
        return NoneDict(**new_opt)
    if isinstance(opt, list):
        return [dict_to_nonedict(sub_opt) for sub_opt in opt]
    return opt

# Test with various input types
simple_dict = {
    'a': 1,
    'b': 'test',
    'c': 2.5
}

nested_dict = {
    'level1': {
        'level2a': 10,
        'level2b': 'nested_value'
    },
    'simple': 42
}

dict_with_list = {
    'items': [1, 2, {'nested': 'in_list'}],
    'value': 'top'
}

list_input = [1, 'string', {'key': 'value'}, [1, 2, 3]]

complex_input = {
    'tensors': torch.randn(2, 4),
    'arrays': np.array([1, 2, 3]),
    'nested': {
        'deep': {
            'value': torch.zeros(2, 4)
        }
    },
    'list': [1, 2, {'inner': 'dict'}]
}

ARGS = {
    'opt': nested_dict
}
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 NoneDict — a NoneDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a NoneDict 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
float_distance Ran
ran on a synthesized input
LCM1999/VolumeRescaling/codes/models/modules/DistanceField.py
code served (permissive licence) · get_code("3516a45279831991")
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

def float_distance(v1, v2):
    x_2 = (v2[0] - v1[0]) ** 2
    y_2 = (v2[1] - v1[1]) ** 2
    z_2 = (v2[2] - v1[2]) ** 2
    return np.sqrt(x_2 + y_2 + z_2)

v1 = np.array([0.0, 0.0, 0.0])
v2 = np.array([1.0, 1.0, 1.0])

ARGS = {
    "v1": v1,
    "v2": v2
}
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 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
linear_warmup_lr Ran
ran, honoured the contract we drafted
JoegameZhou/ms-irn/src/optim/warmup_cosine_annealing_lr.py
code served (permissive licence) · get_code("168634e8dabebd81")
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 torch
import numpy as np

torch.manual_seed(0)

ARGS = {
    "current_step": 5,
    "warmup_steps": 10,
    "base_lr": 0.001,
    "init_lr": 0.0001
}
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 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
linear_warmup_lr Ran
ran, honoured the contract we drafted
JoegameZhou/ms-irn/src/optim/warmup_multisteplr.py
code served (permissive licence) · get_code("e333b3db3a301339")
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 torch

torch.manual_seed(0)

ARGS = {
    "current_step": 5,
    "warmup_steps": 10,
    "base_lr": 0.001,
    "init_lr": 0.0001,
}
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 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
lr_steps Ran
ran on a synthesized input
JoegameZhou/ms-irn/src/optim/warmup_multisteplr.py
code served (permissive licence) · get_code("a6bff4162d391ed8")
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 (995,) 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

# Set up parameters for lr_steps function
global_step = 5
lr_init = 0.0001
lr_max = 0.001
warmup_epochs = 2
total_epochs = 10
steps_per_epoch = 100

ARGS = {
    "global_step": global_step,
    "lr_init": lr_init,
    "lr_max": lr_max,
    "warmup_epochs": warmup_epochs,
    "total_epochs": total_epochs,
    "steps_per_epoch": steps_per_epoch,
}
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 1, dtype family float, shape (995,) — shape (995,) 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_grid Ran
ran on a synthesized input
JoegameZhou/ms-irn/src/utils/util.py
code served (permissive licence) · get_code("13d4333fb600dfdc")
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 float, shape (3, 8, 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 numpy as np
import math

torch.manual_seed(0)

# Create a 4D tensor with shape (B, C, H, W)
# B=2 (batch size), C=3 (RGB channels), H=4 (height), W=5 (width)
tensor = torch.randn(2, 3, 4, 5)

ARGS = {
    "tensor": tensor
}
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 3, dtype family float, shape (3, 8, 5) — shape (3, 8, 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
quantize Ran
ran on a synthesized input
andreasfloros/IRN/utils.py
code served (permissive licence) · get_code("852a7c9de098c70e")
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 (2, 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 as th

th.manual_seed(0)

# Create a small input tensor with values in [0, 1] range
# Using shape (2, 4) for batch size 2, 4 dimensions
inpt = th.rand(2, 4)

ARGS = {
    "inpt": inpt
}
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 2, dtype family float, shape (2, 4) — shape (2, 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
rgb2y Ran
ran on a synthesized input
andreasfloros/IRN/utils.py
code served (permissive licence) · get_code("f64366aa6addd1e3")
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, 1, 4, 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 as th

th.manual_seed(0)

# Create a small RGB tensor with shape (batch=2, channels=3, height=4, width=4)
# The function expects inpt[:, :1, ...], inpt[:, 1:2, ...], inpt[:, 2:, ...]
# which means it indexes by channel dimension at index 1
inpt = th.rand(2, 3, 4, 4)

ARGS = {
    "inpt": inpt
}
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, 1, 4, 4) — shape (2, 1, 4, 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
ssim Ran
ran, honoured the contract we drafted
pkuxmq/Invertible-Image-Rescaling/metrics/calculate_PSNR_SSIM.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from AlifAshrafee/Restoring-Without-Forgetting, is pointer only (licence: NONE) · get_code("ba721aeacc165234")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), 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.

warmup_cosine_annealing_lr Ran
ran on a synthesized input
JoegameZhou/ms-irn/src/optim/warmup_cosine_annealing_lr.py
code served (permissive licence) · get_code("e12f338ec31cda18")
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 (1000,) 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 math
import numpy as np

# Analyze the function signature and usage:
# warmup_cosine_annealing_lr(lr, steps_per_epoch, warmup_epochs, max_epoch, T_max, eta_min=0)
# 
# Parameters used:
# - lr: used as base_lr (float)
# - steps_per_epoch: used in multiplications and divisions (int)
# - warmup_epochs: used in multiplications (int)
# - max_epoch: used in multiplications (int)
# - T_max: used in division for cosine annealing (int)
# - eta_min: used in cosine calculation (float, default 0)

ARGS = {
    "lr": 0.1,
    "steps_per_epoch": 100,
    "warmup_epochs": 2,
    "max_epoch": 10,
    "T_max": 8,
    "eta_min": 1e-6,
}
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 1, dtype family float, shape (1000,) — shape (1000,) 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
warmup_step_lr Ran
ran on a synthesized input
JoegameZhou/ms-irn/src/optim/warmup_multisteplr.py
code served (permissive licence) · get_code("85f7744dc00ae425")
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 (3000,) 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

ARGS = {
    "lr": 0.01,
    "lr_epochs": [10, 20],
    "steps_per_epoch": 100,
    "warmup_epochs": 2,
    "max_epoch": 30,
    "gamma": 0.1
}
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 1, dtype family float, shape (3000,) — shape (3000,) 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
define_IDN Not yet run
unverified (harvested, no recorded run)
LCM1999/VolumeRescaling/codes/models/networks.py
code served (permissive licence) · get_code("4045b447f74b1b70")
How it ran

no invocation recorded.

parse Not yet run
unverified (harvested, no recorded run)
JoegameZhou/ms-irn/src/options/options.py
code served (permissive licence) · get_code("df072befe275ec6a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 0 the same month, 5 later) and 5 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
dict2str 23 other papers
2 dated earlier, 21 later
1905.02716 (2019-05)
EDVR: Video Restoration with Enhanced Deformable Convolutional Networks
1907.03222 (2019-07)
IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
2006.14200 (2020-06)
SRFlow: Learning the Super-Resolution Space with Normalizing Flow
and 20 more not named here
ssim 18 other papers
2 dated earlier, 16 later
1809.00219 (2018-09)
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
1904.03377 (2019-04)
Blind Super-Resolution With Iterative Kernel Correction
and 15 more not named here
calculate_psnr 16 other papers
4 dated earlier, 12 later
1809.00219 (2018-09)
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
1904.03377 (2019-04)
Blind Super-Resolution With Iterative Kernel Correction
1905.02716 (2019-05)
EDVR: Video Restoration with Enhanced Deformable Convolutional Networks
and 13 more not named here
linear_warmup_lr 8 other papers
6 dated earlier, 2 later
1611.06612 (2016-11)
RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation
1811.12814 (2018-11)
Graph-Based Global Reasoning Networks
1907.03222 (2019-07)
IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
and 5 more not named here
calculate_ssim 3 other papers
2 dated earlier, 1 later
1809.00219 (2018-09)
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
1904.03377 (2019-04)
Blind Super-Resolution With Iterative Kernel Correction
2407.09299 (2024-07)
PID: Physics-Informed Diffusion Model for Infrared Image Generation
dict_to_nonedict 1 other paper
1 dated earlier
1907.03222 (2019-07)
IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
lr_steps 1 other paper
1 dated earlier
1907.03222 (2019-07)
IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
make_grid 1 other paper
1 dated earlier
1907.03222 (2019-07)
IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
parse 1 other paper
1 dated earlier
1907.03222 (2019-07)
IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
warmup_cosine_annealing_lr 1 other paper
1 dated earlier
1907.03222 (2019-07)
IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
warmup_step_lr 1 other paper
1 dated earlier
1907.03222 (2019-07)
IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery

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

High-resolution digital images are usually downscaled to fit various display screens or save the cost of storage and bandwidth, meanwhile the post-upscaling is adpoted to recover the original resolutions or the details in the zoom-in images. However, typical image downscaling is a non-injective mapping due to the loss of high-frequency information, which leads to the ill-posed problem of the inverse upscaling procedure and poses great challenges for recovering details from the downscaled low-resolution images. Simply upscaling with image super-resolution methods results in unsatisfactory recovering performance. In this work, we propose to solve this problem by modeling the downscaling and upscaling processes from a new perspective, i.e. an invertible bijective transformation, which can largely mitigate the ill-posed nature of image upscaling. We develop an Invertible Rescaling Net (IRN) with deliberately designed framework and objectives to produce visually-pleasing low-resolution images and meanwhile capture the distribution of the lost information using a latent variable following a specified distribution in the downscaling process. In this way, upscaling is made tractable by inversely passing a randomly-drawn latent variable with the low-resolution image through the network. Experimental results demonstrate the significant improvement of our model over existing methods in terms of both quantitative and qualitative evaluations of image upscaling reconstruction from downscaled images.

For agents

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

get_harvested_code_for_paper("2005.05650")
get_code_for_paper("2005.05650")
have("2005.05650")

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

curl https://syntology.ai/api/ran/2005.05650.json

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

[![Syntology run record](https://syntology.ai/api/ran/2005.05650.svg)](https://syntology.ai/paper/2005.05650)

Connect an agent — have() is free.