SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2001.06826 · 2020

Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement

arXiv · PDF · Open in the Atlas

Code that ran

11 of 16 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, 0 violated it and 8 have no contract verdict; 2 failures of our instrument; 5 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/2001.06826.json · badge: /api/ran/2001.06826.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
cuiziteng/iccv_maet community (classifier label)
classifier basis not recorded on the link
4 ran · 0 no recorded run
tuvovan/Zero_DCE_TF community (classifier label)
classifier basis not recorded on the link
3 ran · 4 no recorded run
canturan10/light_side community (classifier label)
classifier basis not recorded on the link
3 ran · 1 no recorded run
soumik12345/Zero-DCE community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
L_TV Ran
ran on a synthesized input
tuvovan/Zero_DCE_TF/src/loss.py
code served (permissive licence) · get_code("d3351079e85081a6")
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 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 tensorflow as tf
import numpy as np

# Create a small tensor with shape (batch_size, height, width, channels)
# Using distinct sizes: batch=2, height=4, width=3, channels=5
x = tf.constant(np.random.randn(2, 4, 3, 5).astype(np.float32))

# Define ARGS with all parameters
ARGS = {
    'x': x,
    'TVLoss_weight': 1
}
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 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
L_exp Ran
ran on a synthesized input
tuvovan/Zero_DCE_TF/src/loss.py
code served (permissive licence) · get_code("037bf1c6b1f20806")
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 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 tensorflow as tf
import numpy as np

# Create a small input tensor
# The function expects x to be a 4D tensor (batch, height, width, channels)
# We'll use shape (2, 32, 32, 3) - batch of 2, 32x32 spatial dims, 3 channels
x = tf.constant(np.random.randn(2, 32, 32, 3).astype(np.float32))

# Define the function arguments
ARGS = {
    "x": x,
    "mean_val": 0.6
}
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 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
convert_np Ran
ran on a synthesized input
canturan10/light_side/light_side/utils.py
code served (permissive licence) · get_code("5a508e6403e60f0d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Create batch: List[torch.Tensor]
# Each tensor represents an image with shape (C, H, W)
# The function expects values in range [0, 255] for images
batch = [
    torch.randint(0, 256, (3, 4, 5), dtype=torch.float32),
    torch.randint(0, 256, (3, 4, 5), dtype=torch.float32)
]

# Create preds: List[torch.Tensor]
# Each tensor represents predictions with shape (C, H, W)
# The function expects values in range [0, 1] for predictions (mul by 255)
preds = [
    torch.rand(3, 4, 5, dtype=torch.float32),
    torch.rand(3, 4, 5, dtype=torch.float32)
]

ARGS = {
    'batch': batch,
    'preds': preds
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_final_epoch Ran
ran, honoured the contract we drafted
cuiziteng/iccv_maet/.dev_scripts/gather_models.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from mickeykang16/Ev-Stereo3D, is pointer only (licence: NONE) · get_code("e86ae414e2afc197")
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 mickeykang16/Ev-Stereo3D, 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.

get_final_results Ran
ran; our contract draft was wrong, not the code
cuiziteng/iccv_maet/.dev_scripts/gather_models.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from mickeykang16/Ev-Stereo3D, is pointer only (licence: NONE) · get_code("fee6fb3d147348e3")
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 mickeykang16/Ev-Stereo3D, 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.

populate_train_list Ran
ran on a synthesized input
tuvovan/Zero_DCE_TF/src/data_lowlight.py
code served (permissive licence) · get_code("a90a91cfd3bee533")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import random
import glob
import tempfile
import os

# Create a temporary directory with some mock .JPG files
temp_dir = tempfile.mkdtemp()
for i in range(3):
    open(os.path.join(temp_dir, f'image_{i}.JPG'), 'w').close()

lowlight_images_path = temp_dir + os.sep

ARGS = {
    'lowlight_images_path': lowlight_images_path
}
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 list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
pretty_size Ran
ran on a synthesized input
soumik12345/Zero-DCE/zero_dce/utils.py
code served (permissive licence) · get_code("3fa4889eb961839a")
How it ran

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

import torch

torch.manual_seed(0)

# The function expects a torch.Size object
# torch.Size is created from a tensor's .size() method or directly
size_obj = torch.Size([2, 3, 4])

ARGS = {
    "size": size_obj
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
process_checkpoint Ran
ran; our contract draft was wrong, not the code
cuiziteng/iccv_maet/.dev_scripts/gather_models.py
code served (permissive licence) · get_code("e76a491553cf9fcf")
How it ran

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

import torch
import tempfile
import os

torch.manual_seed(0)

# Create a temporary directory for checkpoint files
temp_dir = tempfile.mkdtemp()

# Create a minimal checkpoint dict with a model state and optimizer
checkpoint = {
    'model': {
        'layer1.weight': torch.randn(4, 3),
        'layer1.bias': torch.randn(4),
    },
    'optimizer': {
        'state': {},
        'param_groups': [],
    },
    'epoch': 1,
}

# Save the checkpoint to a temporary file
in_file = os.path.join(temp_dir, 'checkpoint.pth')
torch.save(checkpoint, in_file)

# Define output file path
out_file = os.path.join(temp_dir, 'checkpoint_processed.pth')

ARGS = {
    'in_file': in_file,
    'out_file': out_file,
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
read_imagefile Ran
ran on a synthesized input
canturan10/light_side/deployment/fastapi/service.py
code served (permissive licence) · get_code("e5a657a01454b7f8")
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 PngImageFile. 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
from PIL import Image
from io import BytesIO

# Create a small valid image in memory
# Create a simple 4x3 RGB image
img_array = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)
img = Image.fromarray(img_array, mode='RGB')

# Serialize the image to bytes
img_bytes = BytesIO()
img.save(img_bytes, format='PNG')
img_data = img_bytes.getvalue()

ARGS = {
    'data': img_data
}
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 PngImageFile — a PngImageFile output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PngImageFile 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
save_grad Ran
ran on a synthesized input
cuiziteng/iccv_maet/mmdet/models/detectors/MAET_YOLO/MAET_YOLO.py
code served (permissive licence) · get_code("149d779c3ce51b5d")
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 function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function save_grad takes one parameter: 'name' (a string)
# It returns a hook function that captures gradients
# To test this, we need to:
# 1. Create a simple tensor that requires gradients
# 2. Register the hook with that tensor
# 3. Trigger a backward pass to call the hook

grads = {}

def save_grad(name):
    def hook_fn(grad):
        grads[name] = grad
        return grad
    return hook_fn

# Create a simple tensor that requires gradients
x = torch.randn(2, 4, requires_grad=True)

# Register the hook
hook = save_grad("test_tensor")
x.register_hook(hook)

# Trigger backward to execute the hook
loss = x.sum()
loss.backward()

# Now construct the ARGS dict
# The function takes one parameter: name (a string)
ARGS = {
    "name": "gradient_tensor"
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
visualize Ran
ran on a synthesized input
canturan10/light_side/light_side/utils.py
code served (permissive licence) · get_code("d030fc89c60d67f4")
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 numpy as np
from PIL import Image

# Create two sample images as numpy arrays
# Original image: 4x3 RGB
original_image = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)

# Enhanced image: 4x3 RGB
enhanced_image = np.random.randint(0, 256, (4, 3, 3), dtype=np.uint8)

ARGS = {
    'input': {
        'image': original_image,
        'enhanced': enhanced_image
    }
}
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
DCE_x Not yet run
unverified (harvested, no recorded run)
tuvovan/Zero_DCE_TF/src/model.py
code served (permissive licence) · get_code("e824e99cd0a86afe")
How it ran

no invocation recorded.

L_color Not yet run
unverified (harvested, no recorded run)
tuvovan/Zero_DCE_TF/src/loss.py
code served (permissive licence) · get_code("8ec5ded69fae1885")
How it ran

no invocation recorded.

configure_batch Not yet run
unverified (harvested, no recorded run)
canturan10/light_side/light_side/utils.py
code served (permissive licence) · get_code("33162905c6a70e6a")
How it ran

no invocation recorded.

enhance_frame Not yet run
unverified (harvested, no recorded run)
tuvovan/Zero_DCE_TF/video-dce.py
code served (permissive licence) · get_code("b22c91880d31ebfb")
How it ran

no invocation recorded.

load_model Not yet run
unverified (harvested, no recorded run)
tuvovan/Zero_DCE_TF/video-dce.py
code served (permissive licence) · get_code("619e70eaae247e45")
How it ran

no invocation recorded.

Also present in other papers' code

Of 16 samples lifted from this paper's linked repositories, 16 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 4 later) and 12 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
process_checkpoint 45 other papers
5 dated earlier, 39 later, 1 undated
1904.11490 (2019-04)
RepPoints: Point Set Representation for Object Detection
1906.07155 (2019-06)
MMDetection: Open MMLab Detection Toolbox and Benchmark
1908.05612 (2019-08)
R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
and 42 more not named here
get_final_epoch 35 other papers
4 dated earlier, 30 later, 1 undated
1904.11490 (2019-04)
RepPoints: Point Set Representation for Object Detection
1906.07155 (2019-06)
MMDetection: Open MMLab Detection Toolbox and Benchmark
1908.05612 (2019-08)
R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
and 32 more not named here
get_final_results 8 other papers
4 dated earlier, 4 later
1904.11490 (2019-04)
RepPoints: Point Set Representation for Object Detection
1906.07155 (2019-06)
MMDetection: Open MMLab Detection Toolbox and Benchmark
1908.05612 (2019-08)
R3Det: Refined Single-Stage Detector with Feature Refinement for Rotating Object
and 5 more not named here
save_grad 1 other paper
1 later
2205.03346 (2022-05)
Multitask AET with Orthogonal Tangent Regularity for Dark Object Detection

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

The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network. Our method trains a lightweight deep network, DCE-Net, to estimate pixel-wise and high-order curves for dynamic range adjustment of a given image. The curve estimation is specially designed, considering pixel value range, monotonicity, and differentiability. Zero-DCE is appealing in its relaxed assumption on reference images, i.e., it does not require any paired or unpaired data during training. This is achieved through a set of carefully formulated non-reference loss functions, which implicitly measure the enhancement quality and drive the learning of the network. Our method is efficient as image enhancement can be achieved by an intuitive and simple nonlinear curve mapping. Despite its simplicity, we show that it generalizes well to diverse lighting conditions. Extensive experiments on various benchmarks demonstrate the advantages of our method over state-of-the-art methods qualitatively and quantitatively. Furthermore, the potential benefits of our Zero-DCE to face detection in the dark are discussed. Code and model will be available at https://github.com/Li-Chongyi/Zero-DCE.

For agents

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

get_harvested_code_for_paper("2001.06826")
get_code_for_paper("2001.06826")
have("2001.06826")

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

curl https://syntology.ai/api/ran/2001.06826.json

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

[![Syntology run record](https://syntology.ai/api/ran/2001.06826.svg)](https://syntology.ai/paper/2001.06826)

Connect an agent — have() is free.