SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.06792 · 2020

Learning Enriched Features for Real Image Restoration and Enhancement

arXiv · PDF · Open in the Atlas

Code that ran

12 of 20 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; 0 honoured the contract we drafted, 0 violated it and 9 have no contract verdict; 3 failures of our instrument; 8 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/2003.06792.json · badge: /api/ran/2003.06792.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
venkat2319/Mirnet community (classifier label)
classifier basis not recorded on the link
7 ran · 7 no recorded run
tuvovan/MIRNet---Keras community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
2 ran · 0 no recorded run
sldyns/MIRNet_paddle reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
channel_attention_block Ran
ran on a synthesized input
venkat2319/Mirnet/mirnet/model/dual_attention_unit/attention_blocks.py
code served (permissive licence) · get_code("8e0e5c2b567503d2")
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 EagerTensor, ndim 4, dtype family float, shape (2, 4, 3, 8) 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 tensorflow as tf
import numpy as np

# Create a small input tensor: batch_size=2, height=4, width=3, channels=8
input_tensor = tf.constant(
    np.random.randn(2, 4, 3, 8).astype(np.float32)
)

ARGS = {
    "input_tensor": input_tensor,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 4, dtype family float, shape (2, 4, 3, 8) — shape (2, 4, 3, 8) 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
closest_number Ran
ran on a synthesized input
venkat2319/Mirnet/mirnet/utils.py
code served (permissive licence) · get_code("0c7e98b7a4175fdf")
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
import numpy as np

# Analyze the function:
# - n: appears to be a number (int or float) used in division and arithmetic
# - m: appears to be a number (int or float) used as divisor and multiplier
# - The function performs arithmetic operations: division, multiplication, comparison
# - Returns either n1 or n2, which are multiples of m closest to n

# Set up test arguments
n = 17
m = 5

ARGS = {
    "n": n,
    "m": m
}
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 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
down_sampling_module Ran
ran on a synthesized input
venkat2319/Mirnet/mirnet/model/residual_resizing_modules.py
code served (permissive licence) · get_code("bdaa97ac65e6ada5")
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 EagerTensor, ndim 4, dtype family float, shape (2, 2, 1, 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 tensorflow as tf
import numpy as np

# Set seeds for reproducibility
tf.random.set_seed(0)
np.random.seed(0)

# Create a small input tensor
# Shape: (batch_size, height, width, channels)
# Using distinct dimensions: batch=2, height=4, width=3, channels=5
input_tensor = tf.random.normal(shape=(2, 4, 3, 5), dtype=tf.float32)

ARGS = {
    "input_tensor": input_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 4, dtype family float, shape (2, 2, 1, 10) — shape (2, 2, 1, 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
get_args Ran
ran; our contract draft was wrong, not the code
sldyns/MIRNet_paddle/infer.py
pointer only (licence: NOASSERTION) · get_code("ae39f655cba1d67e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, sldyns/MIRNet_paddle (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_lowres_image Ran
ran on a synthesized input
tuvovan/MIRNet---Keras/utils.py
code served (permissive licence) · get_code("24a751f9bed72798")
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.

import torch
from PIL import Image
import numpy as np

torch.manual_seed(0)

# Create a small PIL Image object
img_array = np.random.randint(0, 256, (100, 80, 3), dtype=np.uint8)
img = Image.fromarray(img_array)

ARGS = {
    'img': img,
    'mode': 'denoise'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
PIL, numpy, torch — 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
psnr Ran
ran on a synthesized input
venkat2319/Mirnet/mirnet/utils.py
code served (permissive licence) · get_code("b6b9b6c72f37dbc2")
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 EagerTensor, ndim 1, dtype family float, shape (2,) 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 tensorflow as tf
import numpy as np

# Create small image tensors for PSNR calculation
# PSNR expects images with pixel values in range [0, max_val]
# Using batch size 2, with distinct spatial dimensions 4x3

y_true = tf.constant(np.random.randint(0, 256, size=(2, 4, 3, 3), dtype=np.uint8), dtype=tf.float32)
y_pred = tf.constant(np.random.randint(0, 256, size=(2, 4, 3, 3), dtype=np.uint8), dtype=tf.float32)

ARGS = {
    'y_true': y_true,
    'y_pred': y_pred,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 1, dtype family float, shape (2,) — shape (2,) 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
random_crop Ran
ran on a synthesized input
tuvovan/MIRNet---Keras/utils.py
code served (permissive licence) · get_code("004145b87f7e0002")
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 4, 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 tensorflow as tf

# Create small test images
# lr_img and hr_img need to be at least (hr_crop_size, hr_crop_size) in spatial dimensions
hr_crop_size = 128

# Create lr_img: shape (256, 256, 3) - larger than crop size to allow random cropping
lr_img = tf.random.normal(shape=(256, 256, 3), dtype=tf.float32)

# Create hr_img: shape (256, 256, 3) - same size as lr_img for this example
hr_img = tf.random.normal(shape=(256, 256, 3), dtype=tf.float32)

ARGS = {
    "lr_img": lr_img,
    "hr_img": hr_img,
    "hr_crop_size": hr_crop_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 4, 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
read_images Ran
ran on a synthesized input
venkat2319/Mirnet/mirnet/dataloader/common.py
code served (permissive licence) · get_code("24a1bd3b90502aa0")
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 _ParallelMapDataset. 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 tensorflow as tf
import tempfile
import os

# Create temporary directory and small PNG files for testing
temp_dir = tempfile.mkdtemp()

# Create minimal valid PNG files (1x1 pixel, RGB)
# PNG header and minimal valid image data
png_data = b'\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x01\x00\x00\x00\x01\x08\x02\x00\x00\x00\x90wS\xde\x00\x00\x00\x0cIDATx\x9cc\xf8\x0f\x00\x00\x01\x01\x00\x05\x18\x0b\xb3\x00\x00\x00\x00IEND\xaeB`\x82'

# Create a few test PNG files
image_files = []
for i in range(2):
    filepath = os.path.join(temp_dir, f'image_{i}.png')
    with open(filepath, 'wb') as f:
        f.write(png_data)
    image_files.append(filepath)

# Create tensor slice of file paths
image_files_tensor = tf.constant(image_files)

ARGS = {
    'image_files': image_files_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type _ParallelMapDataset — a _ParallelMapDataset output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a _ParallelMapDataset 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
spatial_attention_block Ran
ran on a synthesized input
venkat2319/Mirnet/mirnet/model/dual_attention_unit/attention_blocks.py
code served (permissive licence) · get_code("6d70bcbf3768d570")
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 EagerTensor, 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 tensorflow as tf
import numpy as np

# Create a small input tensor
# Shape: (batch_size=2, height=4, width=3, channels=5)
input_tensor = tf.constant(
    np.random.randn(2, 4, 3, 5).astype(np.float32)
)

ARGS = {
    "input_tensor": input_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
to_3d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from gladzhang/Xformer
pointer only; 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 copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

to_4d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
this paper's copy was not recorded; identical code first harvested from gladzhang/Xformer
pointer only; 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 copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

up_sampling_module Ran
ran on a synthesized input
venkat2319/Mirnet/mirnet/model/residual_resizing_modules.py
code served (permissive licence) · get_code("0c84208cefde62f7")
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 EagerTensor, ndim 4, dtype family float, shape (2, 8, 6, 2) 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 tensorflow as tf

# Create a small input tensor with shape (batch=2, height=4, width=3, channels=5)
input_tensor = tf.random.normal((2, 4, 3, 5))

ARGS = {
    'input_tensor': input_tensor
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 4, dtype family float, shape (2, 8, 6, 2) — shape (2, 8, 6, 2) 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
dual_attention_unit_block Not yet run
unverified (harvested, no recorded run)
venkat2319/Mirnet/mirnet/model/dual_attention_unit/dau.py
code served (permissive licence) · get_code("2ebf26d1f976b945")
How it ran

no invocation recorded.

mirnet_model Not yet run
unverified (harvested, no recorded run)
venkat2319/Mirnet/mirnet/model/mirnet_model.py
code served (permissive licence) · get_code("d497c1746ea0f9b8")
How it ran

no invocation recorded.

multi_scale_residual_block Not yet run
unverified (harvested, no recorded run)
venkat2319/Mirnet/mirnet/model/mirnet_model.py
code served (permissive licence) · get_code("0f2455cb54afff72")
How it ran

no invocation recorded.

predict_images Not yet run
unverified (harvested, no recorded run)
tuvovan/MIRNet---Keras/utils.py
code served (permissive licence) · get_code("b3cb48216a7303e7")
How it ran

no invocation recorded.

random_crop Not yet run
unverified (harvested, no recorded run)
venkat2319/Mirnet/mirnet/dataloader/common.py
code served (permissive licence) · get_code("7d848435a0d2da12")
How it ran

no invocation recorded.

random_flip Not yet run
unverified (harvested, no recorded run)
venkat2319/Mirnet/mirnet/dataloader/common.py
code served (permissive licence) · get_code("2a3989cdfa8362a3")
How it ran

no invocation recorded.

recursive_residual_group Not yet run
unverified (harvested, no recorded run)
venkat2319/Mirnet/mirnet/model/mirnet_model.py
code served (permissive licence) · get_code("57ee64d680125fc8")
How it ran

no invocation recorded.

selective_kernel_feature_fusion Not yet run
unverified (harvested, no recorded run)
venkat2319/Mirnet/mirnet/model/skff.py
code served (permissive licence) · get_code("04528d72d04da9ca")
How it ran

no invocation recorded.

Also present in other papers' code

Of 20 samples lifted from this paper's linked repositories, 20 carry a function identity and 0 do not. Of the 20 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 18 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
to_3d 80 other papers
80 later · 18 only as an assembly brick
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
to_4d 79 other papers
79 later · 18 only as an assembly brick
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

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

With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography, medical imaging, and remote sensing. Recently, convolutional neural networks (CNNs) have achieved dramatic improvements over conventional approaches for image restoration task. Existing CNN-based methods typically operate either on full-resolution or on progressively low-resolution representations. In the former case, spatially precise but contextually less robust results are achieved, while in the latter case, semantically reliable but spatially less accurate outputs are generated. In this paper, we present a novel architecture with the collective goals of maintaining spatially-precise high-resolution representations through the entire network and receiving strong contextual information from the low-resolution representations. The core of our approach is a multi-scale residual block containing several key elements: (a) parallel multi-resolution convolution streams for extracting multi-scale features, (b) information exchange across the multi-resolution streams, (c) spatial and channel attention mechanisms for capturing contextual information, and (d) attention based multi-scale feature aggregation. In a nutshell, our approach learns an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details. Extensive experiments on five real image benchmark datasets demonstrate that our method, named as MIRNet, achieves state-of-the-art results for a variety of image processing tasks, including image denoising, super-resolution, and image enhancement. The source code and pre-trained models are available at https://github.com/swz30/MIRNet.

For agents

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

get_harvested_code_for_paper("2003.06792")
get_code_for_paper("2003.06792")
have("2003.06792")

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

curl https://syntology.ai/api/ran/2003.06792.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.06792.svg)](https://syntology.ai/paper/2003.06792)

Connect an agent — have() is free.