SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1805.01934 · 2018

Learning to See in the Dark

arXiv · PDF · Open in the Atlas

Code that ran

8 of 14 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 7 have no contract verdict; 1 failure of our instrument; 6 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/1805.01934.json · badge: /api/ran/1805.01934.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
kauziishere/lowLightImageEnhancement community (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
cchen156/Learning-to-See-in-the-Dark community (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
eoinoreilly30/seeing-in-the-dark reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
cydonia999/Learning_to_See_in_the_Dark_PyTorch community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
ashikshafi08/learning_to_see_in_the_dark_Fastai community (classifier label)
classifier basis not recorded on the link
0 ran · 2 no recorded run
FunctionStatusWhere it lives
create_files Ran
ran on a synthesized input
kauziishere/lowLightImageEnhancement/preprocess.py
code served (permissive licence) · get_code("cf3152406f05fa10")
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 tempfile
import os

# Create temporary files with valid content
temp_dir = tempfile.mkdtemp()

train_file = os.path.join(temp_dir, "train.txt")
test_file = os.path.join(temp_dir, "test.txt")
val_file = os.path.join(temp_dir, "val.txt")

# Write sample data to train file
with open(train_file, 'w') as f:
    f.write("input1.jpg output1.jpg extra1 extra2\n")
    f.write("input2.jpg output2.jpg extra3 extra4\n")

# Write sample data to test file
with open(test_file, 'w') as f:
    f.write("test_input1.jpg test_output1.jpg extra5 extra6\n")
    f.write("test_input2.jpg test_output2.jpg extra7 extra8\n")

# Write sample data to val file
with open(val_file, 'w') as f:
    f.write("val_input1.jpg val_output1.jpg extra9 extra10\n")
    f.write("val_input2.jpg val_output2.jpg extra11 extra12\n")

ARGS = {
    "train_images_file": train_file,
    "test_images_file": test_file,
    "val_images_file": val_file,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type 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
demosaicing Ran
ran on a synthesized input
kauziishere/lowLightImageEnhancement/Traditional.py
code served (permissive licence) · get_code("de6a4c519048370e")
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 (4, 6) 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

# Create a small Bayer pattern image with some NaN values for demosaicing
np.random.seed(0)

# Create a simple 4x6 image array (Bayer pattern simulation)
img_arr = np.random.rand(4, 6).astype(np.float32)

# Introduce some NaN values to simulate missing pixels in demosaicing
img_arr[0, 1] = np.nan
img_arr[1, 3] = np.nan
img_arr[2, 5] = np.nan

imrows = 4
imcols = 6

ARGS = {
    "img_arr": img_arr,
    "imrows": imrows,
    "imcols": imcols,
}
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, shape (4, 6) — shape (4, 6) 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
denoising_sharpening Ran
ran on a synthesized input
kauziishere/lowLightImageEnhancement/Traditional.py
code served (permissive licence) · get_code("8a3d4f41e8538215")
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 (32, 48, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import cv2
import numpy as np

# Create a small colored image (3-channel RGB/BGR image)
# Using uint8 dtype as required by cv2.fastNlMeansDenoisingColored
img_arr = np.random.randint(0, 256, size=(32, 48, 3), dtype=np.uint8)

ARGS = {
    "img_arr": img_arr
}
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 (32, 48, 3) — shape (32, 48, 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
function_to_remove_negs Ran
ran on a synthesized input
kauziishere/lowLightImageEnhancement/model.py
code served (permissive licence) · get_code("853442f9f5fee7a7")
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 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 tensorflow as tf
import numpy as np

# The function takes a single parameter 'x' which should be a tensor-like object
# The function applies tf.maximum(x, 0) to remove negatives, then tf.minimum(..., 1) to cap at 1
# So it clamps x to the range [0, 1]

# Create a small TensorFlow tensor with values that span negative, zero, and positive ranges
x_values = np.array([[-0.5, 0.0, 0.5, 1.5],
                      [-2.0, 0.25, 0.75, 2.0]], dtype=np.float32)
x = tf.constant(x_values)

ARGS = {
    "x": x
}
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 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
lrelu Ran
ran on a synthesized input
cchen156/Learning-to-See-in-the-Dark/train_Fuji.py
code served (permissive licence) · get_code("f406422099514e4c")
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 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 tensorflow as tf
import numpy as np

def lrelu(x):
    return tf.maximum(x * 0.2, x)

# Create a small TensorFlow tensor for testing
x_value = tf.constant([[-1.0, 0.5, -0.3, 2.0], [0.1, -0.8, 1.5, -0.2]], dtype=tf.float32)

ARGS = {
    'x': x_value
}
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 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
pixel_shuffle Ran
ran on a synthesized input
cydonia999/Learning_to_See_in_the_Dark_PyTorch/models/lsid.py
code served (permissive licence) · get_code("83d71e95179cbcfc")
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, 6, 6) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a valid input tensor
# For upscale_factor=2, we need C*r^2 channels, so 4 channels (1*2^2)
# Shape: [batch_size, channels, height, width] = [2, 4, 3, 3]
input_tensor = torch.randn(2, 4, 3, 3)

# Upscale factor
upscale_factor = 2

# depth_first parameter
depth_first = False

ARGS = {
    "input": input_tensor,
    "upscale_factor": upscale_factor,
    "depth_first": depth_first
}
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, 6, 6) — shape (2, 1, 6, 6) 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
read_in_pickle Ran
ran; our contract draft was wrong, not the code
eoinoreilly30/seeing-in-the-dark/adamw_fujifilm.py
pointer only (licence: NONE) · get_code("430f2f205dce4756")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, eoinoreilly30/seeing-in-the-dark 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.

white_balance Ran
ran on a synthesized input
kauziishere/lowLightImageEnhancement/Traditional.py
code served (permissive licence) · get_code("610d5091b3bf0f9f")
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 cv2
import numpy as np

# Create a small BGR image (height=4, width=3, channels=3)
# OpenCV uses BGR format
img_arr = np.random.randint(0, 256, size=(4, 3, 3), dtype=np.uint8)

ARGS = {
    "img_arr": img_arr
}
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
crop_images Not yet run
unverified (harvested, no recorded run)
eoinoreilly30/seeing-in-the-dark/adamw_fujifilm.py
pointer only (licence: NONE) · get_code("6fe3c6e45de063e5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, eoinoreilly30/seeing-in-the-dark 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. No invocation recorded.

function_to_depth_to_space Not yet run
unverified (harvested, no recorded run)
kauziishere/lowLightImageEnhancement/model.py
code served (permissive licence) · get_code("37a55ee112ef2110")
How it ran

no invocation recorded.

get_confirm_token Not yet run
unverified (harvested, no recorded run)
cchen156/Learning-to-See-in-the-Dark/download_models.py
pointer only (licence: MIT); the stored copy get_code serves, from med-air/FedBN, is pointer only (licence: NONE) · get_code("135b3dc835ffe6ad")
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 med-air/FedBN, 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. No invocation recorded.

get_file_content_as_string Not yet run
unverified (harvested, no recorded run)
ashikshafi08/learning_to_see_in_the_dark_Fastai/libs/functionality.py
code served (permissive licence) · get_code("6800b859a41149ac")
How it ran

no invocation recorded.

predict Not yet run
unverified (harvested, no recorded run)
ashikshafi08/learning_to_see_in_the_dark_Fastai/libs/functionality.py
code served (permissive licence) · get_code("c44e194c35a67b4c")
How it ran

no invocation recorded.

upsample_and_concat Not yet run
unverified (harvested, no recorded run)
cchen156/Learning-to-See-in-the-Dark/train_Fuji.py
code served (permissive licence) · get_code("99be22ebba093e63")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 1 the same month, 2 later) and 11 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
get_confirm_token 38 other papers
8 dated earlier, 3 the same month, 27 later
1409.8230 (2014-09)
RENOIR - A Dataset for Real Low-Light Image Noise Reduction
1503.03832 (2015-03)
FaceNet: A Unified Embedding for Face Recognition and Clustering
1506.03134 (2015-06)
Pointer Networks
and 35 more not named here
lrelu 3 other papers
2 dated earlier, 1 later
1603.04042 (2016-03)
Deep Interactive Object Selection
1701.06487 (2017-01)
Dirty Pixels: Towards End-to-End Image Processing and Perception
1908.01311 (2019-08)
Fully Automatic Video Colorization with Self-Regularization and Diversity
upsample_and_concat 1 other paper
1 dated earlier
1701.06487 (2017-01)
Dirty Pixels: Towards End-to-End Image Processing and Perception

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

Imaging in low light is challenging due to low photon count and low SNR. Short-exposure images suffer from noise, while long exposure can induce blur and is often impractical. A variety of denoising, deblurring, and enhancement techniques have been proposed, but their effectiveness is limited in extreme conditions, such as video-rate imaging at night. To support the development of learning-based pipelines for low-light image processing, we introduce a dataset of raw short-exposure low-light images, with corresponding long-exposure reference images. Using the presented dataset, we develop a pipeline for processing low-light images, based on end-to-end training of a fully-convolutional network. The network operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data. We report promising results on the new dataset, analyze factors that affect performance, and highlight opportunities for future work. The results are shown in the supplementary video at https://youtu.be/qWKUFK7MWvg

For agents

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

get_harvested_code_for_paper("1805.01934")
get_code_for_paper("1805.01934")
have("1805.01934")

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

curl https://syntology.ai/api/ran/1805.01934.json

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

[![Syntology run record](https://syntology.ai/api/ran/1805.01934.svg)](https://syntology.ai/paper/1805.01934)

Connect an agent — have() is free.