SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2303.15528 · 2023

Few-Shot Domain Adaptation for Low Light RAW Image Enhancement

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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 6 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/2303.15528.json · badge: /api/ran/2303.15528.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
Vishal-V/FSDA-LowLight canonical (classifier label)
classifier basis not recorded on the link
7 ran · 2 no recorded run
FunctionStatusWhere it lives
gaussian_filter Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Vishal-V/FSDA-LowLight/pytorch_msssim/ssim.py
code served (permissive licence) · get_code("fd04084240f82190")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 4, dtype family float, shape (2, 3, 2, 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 torch
import torch.nn as nn

torch.manual_seed(0)

# Create input tensor: batch_size=2, channels=3, height=4, width=4
input_tensor = torch.randn(2, 3, 4, 4)

# Create 1-D Gaussian kernel window
# The function uses win with shape that allows conv2d with groups=C
# For conv2d with groups=C, kernel shape should be (C, 1, kH, kW)
# We'll create a simple Gaussian kernel: (3, 1, 3, 1) for vertical pass
# and it gets transposed to (3, 1, 1, 3) for horizontal pass
win = torch.randn(3, 1, 3, 1)

ARGS = {
    "input": input_tensor,
    "win": win
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 4, dtype family float, shape (2, 3, 2, 2) — shape (2, 3, 2, 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
ms_ssim Ran
ran on a synthesized input
Vishal-V/FSDA-LowLight/pytorch_msssim/ssim.py
code served (permissive licence) · get_code("9eed7a6520919cad")
How it ran

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

import torch
import torch.nn.functional as F

torch.manual_seed(0)

# Create two small batch images: (N=2, C=3, H=256, W=256)
# Height and width must be large enough for 4 downsamplings with win_size=11
# Minimum: ((11-1) * 2^4) + 1 = 161, so 256 is safe
X = torch.randn(2, 3, 256, 256, dtype=torch.float32)
Y = torch.randn(2, 3, 256, 256, dtype=torch.float32)

ARGS = {
    'X': X,
    'Y': Y,
    'win_size': 11,
    'win_sigma': 1.5,
    'win': None,
    'data_range': 255,
    'size_average': True,
    'full': False,
    'weights': None,
    'K': (0.01, 0.03),
    'nonnegative_ssim': False,
}
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 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
pack_canon Ran
ran on a synthesized input
Vishal-V/FSDA-LowLight/data.py
code served (permissive licence) · get_code("ff4b668dd744d4ee")
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 (4, 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 numpy as np

class RawImage:
    def __init__(self):
        # Create a small raw image with shape (8, 8)
        # Values should be in range that makes sense for raw sensor data
        self.raw_image_visible = np.full((8, 8), 4096, dtype=np.uint16)

raw = RawImage()

ARGS = {
    "raw": raw
}
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 3, dtype family float, shape (4, 4, 4) — shape (4, 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
pack_nikon Ran
ran on a synthesized input
Vishal-V/FSDA-LowLight/data.py
code served (permissive licence) · get_code("ed2e7fcecc58b95a")
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 (64, 64, 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 numpy as np
import cv2

class MockRawImage:
    def __init__(self):
        # Create a small raw image with typical Nikon RAW values
        # Using values in the range that makes sense for the function (600-16383)
        self.raw_image_visible = np.random.randint(600, 16384, size=(128, 128), dtype=np.uint16)

raw_image = MockRawImage()

ARGS = {
    "raw": raw_image,
    "resize": False
}
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 float, shape (64, 64, 4) — shape (64, 64, 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
pack_raw Ran
ran on a synthesized input
Vishal-V/FSDA-LowLight/data.py
code served (permissive licence) · get_code("9b4d83516ecea6fa")
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 (2, 3, 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 numpy as np

class RawImage:
    def __init__(self):
        # Create a small raw image with height=4, width=6
        # Values in range [512, 16383] to ensure positive output after normalization
        self.raw_image_visible = np.random.randint(512, 16383, size=(4, 6), dtype=np.uint16)

raw_obj = RawImage()

ARGS = {
    "raw": raw_obj
}
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 3, dtype family float, shape (2, 3, 4) — shape (2, 3, 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
rgb2gray Ran
ran on a synthesized input
Vishal-V/FSDA-LowLight/train_sony_canon.py
code served (permissive licence) · get_code("587fd1d7356edfe3")
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 5, 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

torch.manual_seed(0)

# The function expects img1 and img2 to be tensors with shape [batch, channels, height, width]
# where batch=1, channels=3 (RGB), and spatial dims can be small
# It accesses img1[0][0], img1[0][1], img1[0][2] which means [batch][channel]
img1 = torch.randn(1, 3, 4, 5)
img2 = torch.randn(1, 3, 4, 5)

device = 'cpu'

ARGS = {
    'img1': img1,
    'img2': img2,
    'device': device
}
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 tuple, ndim 5, 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
ssim_grayscale Ran
ran on a synthesized input
Vishal-V/FSDA-LowLight/train_sony_canon.py
code served (permissive licence) · get_code("661a52e9d4de525c")
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 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
import cv2

torch.manual_seed(0)

# Create mock image tensors with shape (batch, channels, height, width)
# Using distinct dimensions: batch=1, channels=3, height=4, width=5
img1 = torch.rand(1, 3, 4, 5)
img2 = torch.rand(1, 3, 4, 5)

# Create a mock ssim function that accepts two grayscale image tensors
def mock_ssim_fun(img1_gray, img2_gray):
    """Mock SSIM function that takes two grayscale tensors and returns a scalar"""
    # Expected input shape: (1, 1, height, width)
    return torch.tensor(0.95, dtype=torch.double)

# Device set to CPU
device = 'cpu'

ARGS = {
    'img1': img1,
    'img2': img2,
    'ssim_fun': mock_ssim_fun,
    'device': device
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
cv2, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, 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
cos_loss Not yet run
unverified (harvested, no recorded run)
Vishal-V/FSDA-LowLight/train_sony_canon.py
code served (permissive licence) · get_code("5f017c5114d24631")
How it ran

no invocation recorded.

ssim Not yet run
unverified (harvested, no recorded run)
Vishal-V/FSDA-LowLight/pytorch_msssim/ssim.py
code served (permissive licence) · get_code("035c4938516d1fff")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 8 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
gaussian_filter 4 other papers
4 dated earlier
1409.4842 (2014-09)
Going deeper with convolutions
1611.01704 (2016-11)
End-to-end Optimized Image Compression
2001.01568 (2020-01)
Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules
and 1 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 2026-11-22.

Repositories linked to this paper

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

Abstract

Enhancing practical low light raw images is a difficult task due to severe noise and color distortions from short exposure time and limited illumination. Despite the success of existing Convolutional Neural Network (CNN) based methods, their performance is not adaptable to different camera domains. In addition, such methods also require large datasets with short-exposure and corresponding long-exposure ground truth raw images for each camera domain, which is tedious to compile. To address this issue, we present a novel few-shot domain adaptation method to utilize the existing source camera labeled data with few labeled samples from the target camera to improve the target domain's enhancement quality in extreme low-light imaging. Our experiments show that only ten or fewer labeled samples from the target camera domain are sufficient to achieve similar or better enhancement performance than training a model with a large labeled target camera dataset. To support research in this direction, we also present a new low-light raw image dataset captured with a Nikon camera, comprising short-exposure and their corresponding long-exposure ground truth images.

For agents

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

get_harvested_code_for_paper("2303.15528")
get_code_for_paper("2303.15528")
have("2303.15528")

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

curl https://syntology.ai/api/ran/2303.15528.json

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

[![Syntology run record](https://syntology.ai/api/ran/2303.15528.svg)](https://syntology.ai/paper/2303.15528)

Connect an agent — have() is free.